BZPEERPapers, people, evidence and research paths
Menu

Discover

SearchFind papers, people, topics, institutions and opportunities from one place.GraphSee how papers, authors, topics and evidence connect.

Research tools

HomeContinue from the papers, people and topics that matter now.CollectionsTurn saved papers into reading lists, evidence maps and shareable context.ResearchReconstruct the path that led you from search to paper to question.CollaborationMove from a paper, topic or expert request into a focused thread.PublishCreate full-text research articles with metadata, formulas and versions.

Network

ExpertsFind specialists whose work and reviews explain why they can help.CommunitiesJoin research groups organized around papers, topics and shared evidence.

Opportunities

ListingsBrowse roles, calls and collaborations connected to real research context.

Account

Log inReturn to your saved papers, graph views and active threads.Create accountStart saving papers, building a research trail and joining teams.
Log inCreate account

Source author record

Pascal Fua

Pascal Fua appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record
Computer VisionMachine LearningArtificial IntelligenceRoboticsComputational Geometryeess.IVGraphicsmath.OCMathematical Software

Catalog footprint

What is connected

55works
9topics
4close collaborators

Actions

Connect this record

Log in to claim
Open graphBrowse works

Research graph

See the researcher in context

Open full explorer

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

55 published item(s)

preprint2026arXiv

GenMed: A Pairwise Generative Reformulation of Medical Diagnostic Tasks

Data-driven medical AI is traditionally formulated as a discriminative mapping from input $X$ to output $Y$ via a learned function $f$, which does not generalize well across heterogeneous data and modalities encountered in real-world clinical settings. In this work, we propose a fundamentally different, generative paradigm. We model the joint distribution $P(X,Y)$ using diffusion models and reframe inference as a test-time output optimization problem. By guiding the generative process to match observed inputs, our framework enables flexible, gradient-based conditioning at inference time without architectural changes or retraining, effectively supporting arbitrary and previously unseen combinations of observations. Extensive experiments demonstrate strong performance across standard and cross-modality medical image segmentation, few-shot segmentation with only 2 or 4 training samples, degraded-input segmentation, shape completion from sparse and partial observations, and zero-shot application to demonstrate generality. To support these evaluations, we curated and released a large-scale text-shape dataset derived from MedShapeNet. Our results highlight the versatility of generative joint modeling as a foundation for reusable, task-agnostic medical AI systems.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

The MixCount Dataset: Bridging the Data Gap for Open-Vocabulary Object Counting

Object counting is a foundational vision task with over a decade of dedicated research, yet state-of-the-art models still fail systematically in the mixed-object setting that dominates real-world applications such as industrial inspection and product sorting. We show that this gap is strongly driven by limitations in existing training and evaluation data: real counting datasets are prohibitively expensive to annotate and suffer from labeling noise, while existing synthetic alternatives lack diversity and realism. We address this with MixCount, a dataset and benchmark for mixed-object counting designed to target the failure modes of current counting models. To overcome the high cost of constructing and labeling such data, we develop an automatic generation pipeline that synthesizes images, fine-grained textual descriptions, and pixel-perfect counting annotations at scale, eliminating the labeling ambiguity that plagues prior datasets. Evaluating state-of-the-art counting models on MixCount exposes severe degradation in the mixed-object setting. More importantly, training these models on our synthesized data yields substantial gains on real-world benchmarks, reducing MAE by 20.14% on FSC-147 and by 18.3% on PairTally. These results establish MixCount as both a benchmark and a training dataset for fine-grained counting, and demonstrate that our pipeline, which produces effectively unlimited labeled data, helps address a long-standing bottleneck in counting models.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

WindINR: Latent-State INR for Fast Local Wind Query and Correction in Complex Terrain

Many downstream decisions in complex terrain require fast wind estimates at a small number of user-specified locations and heights for a given forecast valid time, rather than another dense forecast field on a fixed grid. We present WindINR, a latent-state implicit neural representation framework for continuous high-resolution local wind query and sparse-observation correction. WindINR maps static terrain descriptors, a low-resolution background field, and continuous query coordinates to a high-resolution wind state through a latent-conditioned decoder. To enable rapid inference-time correction, WindINR separates reusable representation learning from sample-specific latent-state correction. During training, a privileged encoder infers a reference latent state from high-resolution supervision, a deployable latent predictor estimates an initial latent state from inference-time inputs alone, and their discrepancies are summarized into a dataset-adaptive Gaussian prior over latent corrections. At inference time, within the WindINR module, network weights remain fixed and only the latent state is updated by minimizing a regularized correction objective using sparse observations and their uncertainty. In controlled OSSEs over the Senja region, including a UAV-aided approach scenario and random-observation robustness tests, WindINR improves local high-resolution wind estimates by updating only a compact latent state rather than the full network. The corrected representation remains continuously queryable at arbitrary coordinates and, in our CPU benchmark, yields about a $2.6\times$ online-correction speedup over full-network fine-tuning, suggesting a practical interface between kilometer-scale background products, sparse local observations, and wind queries in complex terrain.

0 citations0 reviewsNo code linkedOpen access
preprint2025arXiv

One Graph to Track Them All: Dynamic GNNs for Single- and Multi-View Tracking

This work presents a unified, fully differentiable model for multi-people tracking that learns to associate detections into trajectories without relying on pre-computed tracklets. The model builds a dynamic spatiotemporal graph that aggregates spatial, contextual, and temporal information, enabling seamless information propagation across entire sequences. To improve occlusion handling, the graph can also encode scene-specific information. We also introduce a new large-scale dataset with 25 partially overlapping views, detailed scene reconstructions, and extensive occlusions. Experiments show the model achieves state-of-the-art performance on public benchmarks and the new dataset, with flexibility across diverse conditions. Both the dataset and approach will be publicly released to advance research in multi-people tracking.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

3D Pose Based Feedback for Physical Exercises

Unsupervised self-rehabilitation exercises and physical training can cause serious injuries if performed incorrectly. We introduce a learning-based framework that identifies the mistakes made by a user and proposes corrective measures for easier and safer individual training. Our framework does not rely on hard-coded, heuristic rules. Instead, it learns them from data, which facilitates its adaptation to specific user needs. To this end, we use a Graph Convolutional Network (GCN) architecture acting on the user's pose sequence to model the relationship between the body joints trajectories. To evaluate our approach, we introduce a dataset with 3 different physical exercises. Our approach yields 90.9% mistake identification accuracy and successfully corrects 94.2% of the mistakes.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Deep Active Latent Surfaces for Medical Geometries

Shape priors have long been known to be effective when reconstructing 3D shapes from noisy or incomplete data. When using a deep-learning based shape representation, this often involves learning a latent representation, which can be either in the form of a single global vector or of multiple local ones. The latter allows more flexibility but is prone to overfitting. In this paper, we advocate a hybrid approach representing shapes in terms of 3D meshes with a separate latent vector at each vertex. During training the latent vectors are constrained to have the same value, which avoids overfitting. For inference, the latent vectors are updated independently while imposing spatial regularization constraints. We show that this gives us both flexibility and generalization capabilities, which we demonstrate on several medical image processing tasks.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

DeepMesh: Differentiable Iso-Surface Extraction

Geometric Deep Learning has recently made striking progress with the advent of continuous deep implicit fields. They allow for detailed modeling of watertight surfaces of arbitrary topology while not relying on a 3D Euclidean grid, resulting in a learnable parameterization that is unlimited in resolution. Unfortunately, these methods are often unsuitable for applications that require an explicit mesh-based surface representation because converting an implicit field to such a representation relies on the Marching Cubes algorithm, which cannot be differentiated with respect to the underlying implicit field. In this work, we remove this limitation and introduce a differentiable way to produce explicit surface mesh representations from Deep Implicit Fields. Our key insight is that by reasoning on how implicit field perturbations impact local surface geometry, one can ultimately differentiate the 3D location of surface samples with respect to the underlying deep implicit field. We exploit this to define DeepMesh - an end-to-end differentiable mesh representation that can vary its topology. We validate our theoretical insight through several applications: Single view 3D Reconstruction via Differentiable Rendering, Physically-Driven Shape Optimization, Full Scene 3D Reconstruction from Scans and End-to-End Training. In all cases our end-to-end differentiable parameterization gives us an edge over state-of-the-art algorithms.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Dyadic Human Motion Prediction

Prior work on human motion forecasting has mostly focused on predicting the future motion of single subjects in isolation from their past pose sequence. In the presence of closely interacting people, however, this strategy fails to account for the dependencies between the different subject's motions. In this paper, we therefore introduce a motion prediction framework that explicitly reasons about the interactions of two observed subjects. Specifically, we achieve this by introducing a pairwise attention mechanism that models the mutual dependencies in the motion history of the two subjects. This allows us to preserve the long-term motion dynamics in a more realistic way and more robustly predict unusual and fast-paced movements, such as the ones occurring in a dance scenario. To evaluate this, and because no existing motion prediction datasets depict two closely-interacting subjects, we introduce the LindyHop600K dance dataset. Our results evidence that our approach outperforms the state-of-the-art single person motion prediction techniques.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

HybridSDF: Combining Deep Implicit Shapes and Geometric Primitives for 3D Shape Representation and Manipulation

Deep implicit surfaces excel at modeling generic shapes but do not always capture the regularities present in manufactured objects, which is something simple geometric primitives are particularly good at. In this paper, we propose a representation combining latent and explicit parameters that can be decoded into a set of deep implicit and geometric shapes that are consistent with each other. As a result, we can effectively model both complex and highly regular shapes that coexist in manufactured objects. This enables our approach to manipulate 3D shapes in an efficient and precise manner.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Long Term Motion Prediction Using Keyposes

Long term human motion prediction is essential in safety-critical applications such as human-robot interaction and autonomous driving. In this paper we show that to achieve long term forecasting, predicting human pose at every time instant is unnecessary. Instead, it is more effective to predict a few keyposes and approximate intermediate ones by interpolating the keyposes. We demonstrate that our approach enables us to predict realistic motions for up to 5 seconds in the future, which is far longer than the typical 1 second encountered in the literature. Furthermore, because we model future keyposes probabilistically, we can generate multiple plausible future motions by sampling at inference time. Over this extended time period, our predictions are more realistic, more diverse and better preserve the motion dynamics than those state-of-the-art methods yield.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Neural Annotation Refinement: Development of a New 3D Dataset for Adrenal Gland Analysis

The human annotations are imperfect, especially when produced by junior practitioners. Multi-expert consensus is usually regarded as golden standard, while this annotation protocol is too expensive to implement in many real-world projects. In this study, we propose a method to refine human annotation, named Neural Annotation Refinement (NeAR). It is based on a learnable implicit function, which decodes a latent vector into represented shape. By integrating the appearance as an input of implicit functions, the appearance-aware NeAR fixes the annotation artefacts. Our method is demonstrated on the application of adrenal gland analysis. We first show that the NeAR can repair distorted golden standards on a public adrenal gland segmentation dataset. Besides, we develop a new Adrenal gLand ANalysis (ALAN) dataset with the proposed NeAR, where each case consists of a 3D shape of adrenal gland and its diagnosis label (normal vs. abnormal) assigned by experts. We show that models trained on the shapes repaired by the NeAR can diagnose adrenal glands better than the original ones. The ALAN dataset will be open-source, with 1,584 shapes for adrenal gland diagnosis, which serves as a new benchmark for medical shape analysis. Code and dataset are available at https://github.com/M3DV/NeAR.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

On Triangulation as a Form of Self-Supervision for 3D Human Pose Estimation

Supervised approaches to 3D pose estimation from single images are remarkably effective when labeled data is abundant. However, as the acquisition of ground-truth 3D labels is labor intensive and time consuming, recent attention has shifted towards semi- and weakly-supervised learning. Generating an effective form of supervision with little annotations still poses major challenge in crowded scenes. In this paper we propose to impose multi-view geometrical constraints by means of a weighted differentiable triangulation and use it as a form of self-supervision when no labels are available. We therefore train a 2D pose estimator in such a way that its predictions correspond to the re-projection of the triangulated 3D pose and train an auxiliary network on them to produce the final 3D poses. We complement the triangulation with a weighting mechanism that alleviates the impact of noisy predictions caused by self-occlusion or occlusion from other subjects. We demonstrate the effectiveness of our semi-supervised approach on Human3.6M and MPI-INF-3DHP datasets, as well as on a new multi-view multi-person dataset that features occlusion.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Overcoming the Domain Gap in Neural Action Representations

Relating animal behaviors to brain activity is a fundamental goal in neuroscience, with practical applications in building robust brain-machine interfaces. However, the domain gap between individuals is a major issue that prevents the training of general models that work on unlabeled subjects. Since 3D pose data can now be reliably extracted from multi-view video sequences without manual intervention, we propose to use it to guide the encoding of neural action representations together with a set of neural and behavioral augmentations exploiting the properties of microscopy imaging. To reduce the domain gap, during training, we swap neural and behavioral data across animals that seem to be performing similar actions. To demonstrate this, we test our methods on three very different multimodal datasets; one that features flies and their neural activity, one that contains human neural Electrocorticography (ECoG) data, and lastly the RGB video data of human activities from different viewpoints.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Perspective Flow Aggregation for Data-Limited 6D Object Pose Estimation

Most recent 6D object pose estimation methods, including unsupervised ones, require many real training images. Unfortunately, for some applications, such as those in space or deep under water, acquiring real images, even unannotated, is virtually impossible. In this paper, we propose a method that can be trained solely on synthetic images, or optionally using a few additional real ones. Given a rough pose estimate obtained from a first network, it uses a second network to predict a dense 2D correspondence field between the image rendered using the rough pose and the real image and infers the required pose correction. This approach is much less sensitive to the domain shift between synthetic and real images than state-of-the-art methods. It performs on par with methods that require annotated real images for training when not using any, and outperforms them considerably when using as few as twenty real images.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Weakly Supervised Volumetric Image Segmentation with Deformed Templates

There are many approaches to weakly-supervised training of networks to segment 2D images. By contrast, existing approaches to segmenting volumetric images rely on full-supervision of a subset of 2D slices of the 3D volume. We propose an approach to volume segmentation that is truly weakly-supervised in the sense that we only need to provide a sparse set of 3D points on the surface of target objects instead of detailed 2D masks. We use the 3D points to deform a 3D template so that it roughly matches the target object outlines and we introduce an architecture that exploits the supervision it provides to train a network to find accurate boundaries. We evaluate our approach on Computed Tomography (CT), Magnetic Resonance Imagery (MRI) and Electron Microscopy (EM) image datasets and show that it substantially reduces the required amount of effort.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Image Matching across Wide Baselines: From Paper to Practice

We introduce a comprehensive benchmark for local features and robust estimation algorithms, focusing on the downstream task -- the accuracy of the reconstructed camera pose -- as our primary metric. Our pipeline's modular structure allows easy integration, configuration, and combination of different methods and heuristics. This is demonstrated by embedding dozens of popular algorithms and evaluating them, from seminal works to the cutting edge of machine learning research. We show that with proper settings, classical solutions may still outperform the perceived state of the art. Besides establishing the actual state of the art, the conducted experiments reveal unexpected properties of Structure from Motion (SfM) pipelines that can help improve their performance, for both algorithmic and learned methods. Data and code are online https://github.com/vcg-uvic/image-matching-benchmark, providing an easy-to-use and flexible framework for the benchmarking of local features and robust estimation methods, both alongside and against top-performing methods. This work provides a basis for the Image Matching Challenge https://vision.uvic.ca/image-matching-challenge.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

ActiveMoCap: Optimized Viewpoint Selection for Active Human Motion Capture

The accuracy of monocular 3D human pose estimation depends on the viewpoint from which the image is captured. While freely moving cameras, such as on drones, provide control over this viewpoint, automatically positioning them at the location which will yield the highest accuracy remains an open problem. This is the problem that we address in this paper. Specifically, given a short video sequence, we introduce an algorithm that predicts which viewpoints should be chosen to capture future frames so as to maximize 3D human pose estimation accuracy. The key idea underlying our approach is a method to estimate the uncertainty of the 3D body pose estimates. We integrate several sources of uncertainty, originating from deep learning based regressors and temporal smoothness. Our motion planner yields improved 3D body pose estimates and outperforms or matches existing ones that are based on person following and orbiting.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Comparing Python, Go, and C++ on the N-Queens Problem

Python currently is the dominant language in the field of Machine Learning but is often criticized for being slow to perform certain tasks. In this report, we use the well-known $N$-queens puzzle as a benchmark to show that once compiled using the Numba compiler it becomes competitive with C++ and Go in terms of execution speed while still allowing for very fast prototyping. This is true of both sequential and parallel programs. In most cases that arise in an academic environment, it therefore makes sense to develop in ordinary Python, identify computational bottlenecks, and use Numba to remove them.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Deformation-aware Unpaired Image Translation for Pose Estimation on Laboratory Animals

Our goal is to capture the pose of neuroscience model organisms, without using any manual supervision, to be able to study how neural circuits orchestrate behaviour. Human pose estimation attains remarkable accuracy when trained on real or simulated datasets consisting of millions of frames. However, for many applications simulated models are unrealistic and real training datasets with comprehensive annotations do not exist. We address this problem with a new sim2real domain transfer method. Our key contribution is the explicit and independent modeling of appearance, shape and poses in an unpaired image translation framework. Our model lets us train a pose estimator on the target domain by transferring readily available body keypoint locations from the source domain to generated target images. We compare our approach with existing domain transfer methods and demonstrate improved pose estimation accuracy on Drosophila melanogaster (fruit fly), Caenorhabditis elegans (worm) and Danio rerio (zebrafish), without requiring any manual annotation on the target domain and despite using simplistic off-the-shelf animal characters for simulation, or simple geometric shapes as models. Our new datasets, code, and trained models will be published to support future neuroscientific studies.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Eigendecomposition-Free Training of Deep Networks for Linear Least-Square Problems

Many classical Computer Vision problems, such as essential matrix computation and pose estimation from 3D to 2D correspondences, can be tackled by solving a linear least-square problem, which can be done by finding the eigenvector corresponding to the smallest, or zero, eigenvalue of a matrix representing a linear system. Incorporating this in deep learning frameworks would allow us to explicitly encode known notions of geometry, instead of having the network implicitly learn them from data. However, performing eigendecomposition within a network requires the ability to differentiate this operation. While theoretically doable, this introduces numerical instability in the optimization process in practice. In this paper, we introduce an eigendecomposition-free approach to training a deep network whose loss depends on the eigenvector corresponding to a zero eigenvalue of a matrix predicted by the network. We demonstrate that our approach is much more robust than explicit differentiation of the eigendecomposition using two general tasks, outlier rejection and denoising, with several practical examples including wide-baseline stereo, the perspective-n-point problem, and ellipse fitting. Empirically, our method has better convergence properties and yields state-of-the-art results.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Estimating People Flows to Better Count Them in Crowded Scenes

Modern methods for counting people in crowded scenes rely on deep networks to estimate people densities in individual images. As such, only very few take advantage of temporal consistency in video sequences, and those that do only impose weak smoothness constraints across consecutive frames. In this paper, we advocate estimating people flows across image locations between consecutive images and inferring the people densities from these flows instead of directly regressing. This enables us to impose much stronger constraints encoding the conservation of the number of people. As a result, it significantly boosts performance without requiring a more complex architecture. Furthermore, it also enables us to exploit the correlation between people flow and optical flow to further improve the results. We will demonstrate that we consistently outperform state-of-the-art methods on five benchmark datasets.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

GarNet++: Improving Fast and Accurate Static3D Cloth Draping by Curvature Loss

In this paper, we tackle the problem of static 3D cloth draping on virtual human bodies. We introduce a two-stream deep network model that produces a visually plausible draping of a template cloth on virtual 3D bodies by extracting features from both the body and garment shapes. Our network learns to mimic a Physics-Based Simulation (PBS) method while requiring two orders of magnitude less computation time. To train the network, we introduce loss terms inspired by PBS to produce plausible results and make the model collision-aware. To increase the details of the draped garment, we introduce two loss functions that penalize the difference between the curvature of the predicted cloth and PBS. Particularly, we study the impact of mean curvature normal and a novel detail-preserving loss both qualitatively and quantitatively. Our new curvature loss computes the local covariance matrices of the 3D points, and compares the Rayleigh quotients of the prediction and PBS. This leads to more details while performing favorably or comparably against the loss that considers mean curvature normal vectors in the 3D triangulated meshes. We validate our framework on four garment types for various body shapes and poses. Finally, we achieve superior performance against a recently proposed data-driven method.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Lightweight Multi-View 3D Pose Estimation through Camera-Disentangled Representation

We present a lightweight solution to recover 3D pose from multi-view images captured with spatially calibrated cameras. Building upon recent advances in interpretable representation learning, we exploit 3D geometry to fuse input images into a unified latent representation of pose, which is disentangled from camera view-points. This allows us to reason effectively about 3D pose across different views without using compute-intensive volumetric grids. Our architecture then conditions the learned representation on camera projection operators to produce accurate per-view 2d detections, that can be simply lifted to 3D via a differentiable Direct Linear Transform (DLT) layer. In order to do it efficiently, we propose a novel implementation of DLT that is orders of magnitude faster on GPU architectures than standard SVD-based triangulation methods. We evaluate our approach on two large-scale human pose datasets (H36M and Total Capture): our method outperforms or performs comparably to the state-of-the-art volumetric methods, while, unlike them, yielding real-time performance.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Promoting Connectivity of Network-Like Structures by Enforcing Region Separation

We propose a novel, connectivity-oriented loss function for training deep convolutional networks to reconstruct network-like structures, like roads and irrigation canals, from aerial images. The main idea behind our loss is to express the connectivity of roads, or canals, in terms of disconnections that they create between background regions of the image. In simple terms, a gap in the predicted road causes two background regions, that lie on the opposite sides of a ground truth road, to touch in prediction. Our loss function is designed to prevent such unwanted connections between background regions, and therefore close the gaps in predicted roads. It also prevents predicting false positive roads and canals by penalizing unwarranted disconnections of background regions. In order to capture even short, dead-ending road segments, we evaluate the loss in small image crops. We show, in experiments on two standard road benchmarks and a new data set of irrigation canals, that convnets trained with our loss function recover road connectivity so well, that it suffices to skeletonize their output to produce state of the art maps. A distinct advantage of our approach is that the loss can be plugged in to any existing training setup without further modifications.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Real-Time Camera Pose Estimation for Sports Fields

Given an image sequence featuring a portion of a sports field filmed by a moving and uncalibrated camera, such as the one of the smartphones, our goal is to compute automatically in real time the focal length and extrinsic camera parameters for each image in the sequence without using a priori knowledges of the position and orientation of the camera. To this end, we propose a novel framework that combines accurate localization and robust identification of specific keypoints in the image by using a fully convolutional deep architecture. Our algorithm exploits both the field lines and the players' image locations, assuming their ground plane positions to be given, to achieve accuracy and robustness that is beyond the current state of the art. We will demonstrate its effectiveness on challenging soccer, basketball, and volleyball benchmark datasets.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Single-Stage 6D Object Pose Estimation

Most recent 6D pose estimation frameworks first rely on a deep network to establish correspondences between 3D object keypoints and 2D image locations and then use a variant of a RANSAC-based Perspective-n-Point (PnP) algorithm. This two-stage process, however, is suboptimal: First, it is not end-to-end trainable. Second, training the deep network relies on a surrogate loss that does not directly reflect the final 6D pose estimation task. In this work, we introduce a deep architecture that directly regresses 6D poses from correspondences. It takes as input a group of candidate correspondences for each 3D keypoint and accounts for the fact that the order of the correspondences within each group is irrelevant, while the order of the groups, that is, of the 3D keypoints, is fixed. Our architecture is generic and can thus be exploited in conjunction with existing correspondence-extraction networks so as to yield single-stage 6D pose estimation frameworks. Our experiments demonstrate that these single-stage frameworks consistently outperform their two-stage counterparts in terms of both accuracy and speed.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

TopoAL: An Adversarial Learning Approach for Topology-Aware Road Segmentation

Most state-of-the-art approaches to road extraction from aerial images rely on a CNN trained to label road pixels as foreground and remainder of the image as background. The CNN is usually trained by minimizing pixel-wise losses, which is less than ideal to produce binary masks that preserve the road network's global connectivity. To address this issue, we introduce an Adversarial Learning (AL) strategy tailored for our purposes. A naive one would treat the segmentation network as a generator and would feed its output along with ground-truth segmentations to a discriminator. It would then train the generator and discriminator jointly. We will show that this is not enough because it does not capture the fact that most errors are local and need to be treated as such. Instead, we use a more sophisticated discriminator that returns a label pyramid describing what portions of the road network are correct at several different scales. This discriminator and the structured labels it returns are what gives our approach its edge and we will show that it outperforms state-of-the-art ones on the challenging RoadTracer dataset.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

UCLID-Net: Single View Reconstruction in Object Space

Most state-of-the-art deep geometric learning single-view reconstruction approaches rely on encoder-decoder architectures that output either shape parametrizations or implicit representations. However, these representations rarely preserve the Euclidean structure of the 3D space objects exist in. In this paper, we show that building a geometry preserving 3-dimensional latent space helps the network concurrently learn global shape regularities and local reasoning in the object coordinate space and, as a result, boosts performance. We demonstrate both on ShapeNet synthetic images, which are often used for benchmarking purposes, and on real-world images that our approach outperforms state-of-the-art ones. Furthermore, the single-view pipeline naturally extends to multi-view reconstruction, which we also show.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Using Depth for Pixel-Wise Detection of Adversarial Attacks in Crowd Counting

State-of-the-art methods for counting people in crowded scenes rely on deep networks to estimate crowd density. While effective, deep learning approaches are vulnerable to adversarial attacks, which, in a crowd-counting context, can lead to serious security issues. However, attack and defense mechanisms have been virtually unexplored in regression tasks, let alone for crowd density estimation. In this paper, we investigate the effectiveness of existing attack strategies on crowd-counting networks, and introduce a simple yet effective pixel-wise detection mechanism. It builds on the intuition that, when attacking a multitask network, in our case estimating crowd density and scene depth, both outputs will be perturbed, and thus the second one can be used for detection purposes. We will demonstrate that this significantly outperforms heuristic and uncertainty-based strategies.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Voxel2Mesh: 3D Mesh Model Generation from Volumetric Data

CNN-based volumetric methods that label individual voxels now dominate the field of biomedical segmentation. However, 3D surface representations are often required for proper analysis. They can be obtained by post-processing the labeled volumes which typically introduces artifacts and prevents end-to-end training. In this paper, we therefore introduce a novel architecture that goes directly from 3D image volumes to 3D surfaces without post-processing and with better accuracy than current methods. We evaluate it on Electron Microscopy and MRI brain images as well as CT liver scans. We will show that it outperforms state-of-the-art segmentation methods.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

XNect: Real-time Multi-Person 3D Motion Capture with a Single RGB Camera

We present a real-time approach for multi-person 3D motion capture at over 30 fps using a single RGB camera. It operates successfully in generic scenes which may contain occlusions by objects and by other people. Our method operates in subsequent stages. The first stage is a convolutional neural network (CNN) that estimates 2D and 3D pose features along with identity assignments for all visible joints of all individuals.We contribute a new architecture for this CNN, called SelecSLS Net, that uses novel selective long and short range skip connections to improve the information flow allowing for a drastically faster network without compromising accuracy. In the second stage, a fully connected neural network turns the possibly partial (on account of occlusion) 2Dpose and 3Dpose features for each subject into a complete 3Dpose estimate per individual. The third stage applies space-time skeletal model fitting to the predicted 2D and 3D pose per subject to further reconcile the 2D and 3D pose, and enforce temporal coherence. Our method returns the full skeletal pose in joint angles for each subject. This is a further key distinction from previous work that do not produce joint angle results of a coherent skeleton in real time for multi-person scenes. The proposed system runs on consumer hardware at a previously unseen speed of more than 30 fps given 512x320 images as input while achieving state-of-the-art accuracy, which we will demonstrate on a range of challenging real-world scenes.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Direct Prediction of 3D Body Poses from Motion Compensated Sequences

We propose an efficient approach to exploiting motion information from consecutive frames of a video sequence to recover the 3D pose of people. Previous approaches typically compute candidate poses in individual frames and then link them in a post-processing step to resolve ambiguities. By contrast, we directly regress from a spatio-temporal volume of bounding boxes to a 3D pose in the central frame. We further show that, for this approach to achieve its full potential, it is essential to compensate for the motion in consecutive frames so that the subject remains centered. This then allows us to effectively overcome ambiguities and improve upon the state-of-the-art by a large margin on the Human3.6m, HumanEva, and KTH Multiview Football 3D human pose estimation benchmarks.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Do We Need Binary Features for 3D Reconstruction?

Binary features have been incrementally popular in the past few years due to their low memory footprints and the efficient computation of Hamming distance between binary descriptors. They have been shown with promising results on some real time applications, e.g., SLAM, where the matching operations are relative few. However, in computer vision, there are many applications such as 3D reconstruction requiring lots of matching operations between local features. Therefore, a natural question is that is the binary feature still a promising solution to this kind of applications? To get the answer, this paper conducts a comparative study of binary features and their matching methods on the context of 3D reconstruction in a recently proposed large scale mutliview stereo dataset. Our evaluations reveal that not all binary features are capable of this task. Most of them are inferior to the classical SIFT based method in terms of reconstruction accuracy and completeness with a not significant better computational performance.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Globally Consistent Multi-People Tracking using Motion Patterns

Many state-of-the-art approaches to people tracking rely on detecting them in each frame independently, grouping detections into short but reliable trajectory segments, and then further grouping them into full trajectories. This grouping typically relies on imposing local smoothness constraints but almost never on enforcing more global constraints on the trajectories. In this paper, we propose an approach to imposing global consistency by first inferring behavioral patterns from the ground truth and then using them to guide the tracking algorithm. When used in conjunction with several state-of-the-art algorithms, this further increases their already good performance. Furthermore, we propose an unsupervised scheme that yields almost similar improvements without the need for ground truth.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Globally Optimal Cell Tracking using Integer Programming

We propose a novel approach to automatically tracking cell populations in time-lapse images. To account for cell occlusions and overlaps, we introduce a robust method that generates an over-complete set of competing detection hypotheses. We then perform detection and tracking simultaneously on these hypotheses by solving to optimality an integer program with only one type of flow variables. This eliminates the need for heuristics to handle missed detections due to occlusions and complex morphology. We demonstrate the effectiveness of our approach on a range of challenging sequences consisting of clumped cells and show that it outperforms state-of-the-art techniques.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Learning to Assign Orientations to Feature Points

We show how to train a Convolutional Neural Network to assign a canonical orientation to feature points given an image patch centered on the feature point. Our method improves feature point matching upon the state-of-the art and can be used in conjunction with any existing rotation sensitive descriptors. To avoid the tedious and almost impossible task of finding a target orientation to learn, we propose to use Siamese networks which implicitly find the optimal orientations during training. We also propose a new type of activation function for Neural Networks that generalizes the popular ReLU, maxout, and PReLU activation functions. This novel activation performs better for our task. We validate the effectiveness of our method extensively with four existing datasets, including two non-planar datasets, as well as our own dataset. We show that we outperform the state-of-the-art without the need of retraining for each dataset.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

LIFT: Learned Invariant Feature Transform

We introduce a novel Deep Network architecture that implements the full feature point handling pipeline, that is, detection, orientation estimation, and feature description. While previous works have successfully tackled each one of these problems individually, we show how to learn to do all three in a unified manner while preserving end-to-end differentiability. We then demonstrate that our Deep pipeline outperforms state-of-the-art methods on a number of benchmark datasets, without the need of retraining.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Multi-Modal Mean-Fields via Cardinality-Based Clamping

Mean Field inference is central to statistical physics. It has attracted much interest in the Computer Vision community to efficiently solve problems expressible in terms of large Conditional Random Fields. However, since it models the posterior probability distribution as a product of marginal probabilities, it may fail to properly account for important dependencies between variables. We therefore replace the fully factorized distribution of Mean Field by a weighted mixture of such distributions, that similarly minimizes the KL-Divergence to the true posterior. By introducing two new ideas, namely, conditioning on groups of variables instead of single ones and using a parameter of the conditional random field potentials, that we identify to the temperature in the sense of statistical physics to select such groups, we can perform this minimization efficiently. Our extension of the clamping method proposed in previous works allows us to both produce a more descriptive approximation of the true posterior and, inspired by the diverse MAP paradigms, fit a mixture of Mean Field approximations. We demonstrate that this positively impacts real-world algorithms that initially relied on mean fields.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Social Scene Understanding: End-to-End Multi-Person Action Localization and Collective Activity Recognition

We present a unified framework for understanding human social behaviors in raw image sequences. Our model jointly detects multiple individuals, infers their social actions, and estimates the collective actions with a single feed-forward pass through a neural network. We propose a single architecture that does not rely on external detection algorithms but rather is trained end-to-end to generate dense proposal maps that are refined via a novel inference scheme. The temporal consistency is handled via a person-level matching Recurrent Neural Network. The complete model takes as input a sequence of frames and outputs detections along with the estimates of individual actions and collective activities. We demonstrate state-of-the-art performance of our algorithm on multiple publicly available benchmarks.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Structured Prediction of 3D Human Pose with Deep Neural Networks

Most recent approaches to monocular 3D pose estimation rely on Deep Learning. They either train a Convolutional Neural Network to directly regress from image to 3D pose, which ignores the dependencies between human joints, or model these dependencies via a max-margin structured learning framework, which involves a high computational cost at inference time. In this paper, we introduce a Deep Learning regression architecture for structured prediction of 3D human pose from monocular images that relies on an overcomplete auto-encoder to learn a high-dimensional latent pose representation and account for joint dependencies. We demonstrate that our approach outperforms state-of-the-art ones both in terms of structure preservation and prediction accuracy.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Uniform Information Segmentation

Size uniformity is one of the main criteria of superpixel methods. But size uniformity rarely conforms to the varying content of an image. The chosen size of the superpixels therefore represents a compromise - how to obtain the fewest superpixels without losing too much important detail. We propose that a more appropriate criterion for creating image segments is information uniformity. We introduce a novel method for segmenting an image based on this criterion. Since information is a natural way of measuring image complexity, our proposed algorithm leads to image segments that are smaller and denser in areas of high complexity and larger in homogeneous regions, thus simplifying the image while preserving its details. Our algorithm is simple and requires just one input parameter - a threshold on the information content. On segmentation comparison benchmarks it proves to be superior to the state-of-the-art. In addition, our method is computationally very efficient, approaching real-time performance, and is easily extensible to three-dimensional image stacks and video volumes.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

A provably convergent alternating minimization method for mean field inference

Mean-Field is an efficient way to approximate a posterior distribution in complex graphical models and constitutes the most popular class of Bayesian variational approximation methods. In most applications, the mean field distribution parameters are computed using an alternate coordinate minimization. However, the convergence properties of this algorithm remain unclear. In this paper, we show how, by adding an appropriate penalization term, we can guarantee convergence to a critical point, while keeping a closed form update at each step. A convergence rate estimate can also be derived based on recent results in non-convex optimization.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Active Learning for Delineation of Curvilinear Structures

Many recent delineation techniques owe much of their increased effectiveness to path classification algorithms that make it possible to distinguish promising paths from others. The downside of this development is that they require annotated training data, which is tedious to produce. In this paper, we propose an Active Learning approach that considerably speeds up the annotation process. Unlike standard ones, it takes advantage of the specificities of the delineation problem. It operates on a graph and can reduce the training set size by up to 80% without compromising the reconstruction quality. We will show that our approach outperforms conventional ones on various biomedical and natural image datasets, thus showing that it is broadly applicable.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Dense image registration and deformable surface reconstruction in presence of occlusions and minimal texture

Deformable surface tracking from monocular images is well-known to be under-constrained. Occlusions often make the task even more challenging, and can result in failure if the surface is not sufficiently textured. In this work, we explicitly address the problem of 3D reconstruction of poorly textured, occluded surfaces, proposing a framework based on a template-matching approach that scales dense robust features by a relevancy score. Our approach is extensively compared to current methods employing both local feature matching and dense template alignment. We test on standard datasets as well as on a new dataset (that will be made publicly available) of a sparsely textured, occluded surface. Our framework achieves state-of-the-art results for both well and poorly textured, occluded surfaces.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Introducing Geometry in Active Learning for Image Segmentation

We propose an Active Learning approach to training a segmentation classifier that exploits geometric priors to streamline the annotation process in 3D image volumes. To this end, we use these priors not only to select voxels most in need of annotation but to guarantee that they lie on 2D planar patch, which makes it much easier to annotate than if they were randomly distributed in the volume. A simplified version of this approach is effective in natural 2D images. We evaluated our approach on Electron Microscopy and Magnetic Resonance image volumes, as well as on natural images. Comparing our approach against several accepted baselines demonstrates a marked performance increase.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Modeling Brain Circuitry over a Wide Range of Scales

If we are ever to unravel the mysteries of brain function at its most fundamental level, we will need a precise understanding of how its component neurons connect to each other. Electron Microscopes (EM) can now provide the nanometer resolution that is needed to image synapses, and therefore connections, while Light Microscopes (LM) see at the micrometer resolution required to model the 3D structure of the dendritic network. Since both the topology and the connection strength are integral parts of the brain's wiring diagram, being able to combine these two modalities is critically important. In fact, these microscopes now routinely produce high-resolution imagery in such large quantities that the bottleneck becomes automated processing and interpretation, which is needed for such data to be exploited to its full potential. In this paper, we briefly review the Computer Vision techniques we have developed at EPFL to address this need. They include delineating dendritic arbors from LM imagery, segmenting organelles from EM, and combining the two into a consistent representation.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Predicting People's 3D Poses from Short Sequences

We propose an efficient approach to exploiting motion information from consecutive frames of a video sequence to recover the 3D pose of people. Instead of computing candidate poses in individual frames and then linking them, as is often done, we regress directly from a spatio-temporal block of frames to a 3D pose in the central one. We will demonstrate that this approach allows us to effectively overcome ambiguities and to improve upon the state-of-the-art on challenging sequences.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Principled Parallel Mean-Field Inference for Discrete Random Fields

Mean-field variational inference is one of the most popular approaches to inference in discrete random fields. Standard mean-field optimization is based on coordinate descent and in many situations can be impractical. Thus, in practice, various parallel techniques are used, which either rely on ad-hoc smoothing with heuristically set parameters, or put strong constraints on the type of models. In this paper, we propose a novel proximal gradient-based approach to optimizing the variational objective. It is naturally parallelizable and easy to implement. We prove its convergence, and then demonstrate that, in practice, it yields faster convergence and often finds better optima than more traditional mean-field optimization techniques. Moreover, our method is less sensitive to the choice of parameters.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Template-based Monocular 3D Shape Recovery using Laplacian Meshes

We show that by extending the Laplacian formalism, which was first introduced in the Graphics community to regularize 3D meshes, we can turn the monocular 3D shape reconstruction of a deformable surface given correspondences with a reference image into a much better-posed problem. This allows us to quickly and reliably eliminate outliers by simply solving a linear least squares problem. This yields an initial 3D shape estimate, which is not necessarily accurate, but whose 2D projections are. The initial shape is then refined by a constrained optimization problem to output the final surface reconstruction. Our approach allows us to reduce the dimensionality of the surface reconstruction problem without sacrificing accuracy, thus allowing for real-time implementations.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

TILDE: A Temporally Invariant Learned DEtector

We introduce a learning-based approach to detect repeatable keypoints under drastic imaging changes of weather and lighting conditions to which state-of-the-art keypoint detectors are surprisingly sensitive. We first identify good keypoint candidates in multiple training images taken from the same viewpoint. We then train a regressor to predict a score map whose maxima are those points so that they can be found by simple non-maximum suppression. As there are no standard datasets to test the influence of these kinds of changes, we created our own, which we will make publicly available. We will show that our method significantly outperforms the state-of-the-art methods in such challenging conditions, while still achieving state-of-the-art performance on the untrained standard Oxford dataset.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

What Players do with the Ball: A Physically Constrained Interaction Modeling

Tracking the ball is critical for video-based analysis of team sports. However, it is difficult, especially in low-resolution images, due to the small size of the ball, its speed that creates motion blur, and its often being occluded by players. In this paper, we propose a generic and principled approach to modeling the interaction between the ball and the players while also imposing appropriate physical constraints on the ball's trajectory. We show that our approach, formulated in terms of a Mixed Integer Program, is more robust and more accurate than several state-of-the-art approaches on real-life volleyball, basketball, and soccer sequences.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

Beyond KernelBoost

In this Technical Report we propose a set of improvements with respect to the KernelBoost classifier presented in [Becker et al., MICCAI 2013]. We start with a scheme inspired by Auto-Context, but that is suitable in situations where the lack of large training sets poses a potential problem of overfitting. The aim is to capture the interactions between neighboring image pixels to better regularize the boundaries of segmented regions. As in Auto-Context [Tu et al., PAMI 2009] the segmentation process is iterative and, at each iteration, the segmentation results for the previous iterations are taken into account in conjunction with the image itself. However, unlike in [Tu et al., PAMI 2009], we organize our recursion so that the classifiers can progressively focus on difficult-to-classify locations. This lets us exploit the power of the decision-tree paradigm while avoiding over-fitting. In the context of this architecture, KernelBoost represents a powerful building block due to its ability to learn on the score maps coming from previous iterations. We first introduce two important mechanisms to empower the KernelBoost classifier, namely pooling and the clustering of positive samples based on the appearance of the corresponding ground-truth. These operations significantly contribute to increase the effectiveness of the system on biomedical images, where texture plays a major role in the recognition of the different image components. We then present some other techniques that can be easily integrated in the KernelBoost framework to further improve the accuracy of the final segmentation. We show extensive results on different medical image datasets, including some multi-label tasks, on which our method is shown to outperform state-of-the-art approaches. The resulting segmentations display high accuracy, neat contours, and reduced noise.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

Flying Objects Detection from a Single Moving Camera

We propose an approach to detect flying objects such as UAVs and aircrafts when they occupy a small portion of the field of view, possibly moving against complex backgrounds, and are filmed by a camera that itself moves. Solving such a difficult problem requires combining both appearance and motion cues. To this end we propose a regression-based approach to motion stabilization of local image patches that allows us to achieve effective classification on spatio-temporal image cubes and outperform state-of-the-art techniques. As the problem is relatively new, we collected two challenging datasets for UAVs and Aircrafts, which can be used as benchmarks for flying objects detection and vision-guided collision avoidance.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

On Rendering Synthetic Images for Training an Object Detector

We propose a novel approach to synthesizing images that are effective for training object detectors. Starting from a small set of real images, our algorithm estimates the rendering parameters required to synthesize similar images given a coarse 3D model of the target object. These parameters can then be reused to generate an unlimited number of training images of the object of interest in arbitrary 3D poses, which can then be used to increase classification performances. A key insight of our approach is that the synthetically generated images should be similar to real images, not in terms of image quality, but rather in terms of features used during the detector training. We show in the context of drone, plane, and car detection that using such synthetically generated images yields significantly better performances than simply perturbing real images or even synthesizing images in such way that they look very realistic, as is often done when only limited amounts of training data are available.

0 citations0 reviewsNo code linkedOpen access
preprint2013arXiv

Deriving And Combining Continuous Possibility Functions in the Framework of Evidential Reasoning

To develop an approach to utilizing continuous statistical information within the Dempster- Shafer framework, we combine methods proposed by Strat and by Shafero We first derive continuous possibility and mass functions from probability-density functions. Then we propose a rule for combining such evidence that is simpler and more efficiently computed than Dempster's rule. We discuss the relationship between Dempster's rule and our proposed rule for combining evidence over continuous frames.

0 citations0 reviewsNo code linkedOpen access