Topic overview

Graphics

1417 works4527 researchers

Computer Vision

Open map Browse papers

Map preview

Start with the graph, then narrow the list

1417works

4527researchers

Next steps

Use the topic as a working map

Open the full map for clusters, then return here to scan ranked papers and people.

Inspect nearby papers, researchers, institutions and communities without opening a separate graph page.

Building this map preview

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

preprint2016arXiv

Digital Makeup from Internet Images

We present a novel approach of color transfer between images by exploring their high-level semantic information. First, we set up a database which consists of the collection of downloaded images from the internet, which are segmented automatically by using matting techniques. We then, extract image foregrounds from both source and multiple target images. Then by using image matting algorithms, the system extracts the semantic information such as faces, lips, teeth, eyes, eyebrows, etc., from the extracted foregrounds of the source image. And, then the color is transferred between corresponding parts with the same semantic information. Next we get the color transferred result by seamlessly compositing different parts together using alpha blending. In the final step, we present an efficient method of color consistency to optimize the color of a collection of images showing the common scene. The main advantage of our method over existing techniques is that it does not need face matching, as one could use more than one target images. It is not restricted to head shot images as we can also change the color style in the wild. Moreover, our algorithm does not require to choose the same co

preprint2016arXiv

Fast color transfer from multiple images

Color transfer between images uses the statistics information of image effectively. We present a novel approach of local color transfer between images based on the simple statistics and locally linear embedding. A sketching interface is proposed for quickly and easily specifying the color correspondences between target and source image. The user can specify the correspondences of local region using scribes, which more accurately transfers the target color to the source image while smoothly preserving the boundaries, and exhibits more natural output results. Our algorithm is not restricted to one-to-one image color transfer and can make use of more than one target images to transfer the color in different regions in the source image. Moreover, our algorithm does not require to choose the same color style and image size between source and target images. We propose the sub-sampling to reduce the computational load. Comparing with other approaches, our algorithm is much better in color blending in the input data. Our approach preserves the other color details in the source image. Various experimental results show that our approach specifies the correspondences of local color region in

preprint2016arXiv

Data-driven Shoulder Inverse Kinematics

This paper proposes a shoulder inverse kinematics (IK) technique. Shoulder complex is comprised of the sternum, clavicle, ribs, scapula, humerus, and four joints. The shoulder complex shows specific motion pattern, such as Scapulo humeral rhythm. As a result, if a motion of the shoulder isgenerated without the knowledge of kinesiology, it will be seen as un-natural. The proposed technique generates motion of the shoulder complex about the orientation of the upper arm by interpolating the measurement data. The shoulder IK method allows novice animators to generate natural shoulder motions easily. As a result, this technique improves the quality of character animation.

preprint2016arXiv

Orthogonal Edge Routing for the EditLens

The EditLens is an interactive lens technique that supports the editing of graphs. The user can insert, update, or delete nodes and edges while maintaining an already existing layout of the graph. For the nodes and edges that are affected by an edit operation, the EditLens suggests suitable locations and routes, which the user can accept or adjust. For this purpose, the EditLens requires an efficient routing algorithm that can compute results at interactive framerates. Existing algorithms cannot fully satisfy the needs of the EditLens. This paper describes a novel algorithm that can compute orthogonal edge routes for incremental edit operations of graphs. Tests indicate that, in general, the algorithm is better than alternative solutions.

preprint2016arXiv

Fast Patch-based Style Transfer of Arbitrary Style

Artistic style transfer is an image synthesis problem where the content of an image is reproduced with the style of another. Recent works show that a visually appealing style transfer can be achieved by using the hidden activations of a pretrained convolutional neural network. However, existing methods either apply (i) an optimization procedure that works for any style image but is very expensive, or (ii) an efficient feedforward network that only allows a limited number of trained styles. In this work we propose a simpler optimization objective based on local matching that combines the content structure and style textures in a single layer of the pretrained network. We show that our objective has desirable properties such as a simpler optimization landscape, intuitive parameter tuning, and consistent frame-by-frame performance on video. Furthermore, we use 80,000 natural images and 80,000 paintings to train an inverse network that approximates the result of the optimization. This results in a procedure for artistic style transfer that is efficient but also allows arbitrary content and style images.

preprint2016arXiv

A Qualitative and Quantitative Evaluation of 8 Clear Sky Models

We provide a qualitative and quantitative evaluation of 8 clear sky models used in Computer Graphics. We compare the models with each other as well as with measurements and with a reference model from the physics community. After a short summary of the physics of the problem, we present the measurements and the reference model, and how we "invert" it to get the model parameters. We then give an overview of each CG model, and detail its scope, its algorithmic complexity, and its results using the same parameters as in the reference model. We also compare the models with a perceptual study. Our quantitative results confirm that the less simplifications and approximations are used to solve the physical equations, the more accurate are the results. We conclude with a discussion of the advantages and drawbacks of each model, and how to further improve their accuracy.

preprint2016arXiv

CFD results calibration from sparse sensor observations with a case study for indoor thermal map

Current CFD calibration work has mainly focused on the CFD model calibration. However no known work has considered the calibration of the CFD results. In this paper, we take inspiration from the image editing problem to develop a methodology to calibrate CFD simulation results based on sparse sensor observations. We formulate the calibration of CFD results as an optimization problem. The cost function consists of two terms. One term guarantees a good local adjustment of the simulation results based on the sparse sensor observations. The other term transmits the adjustment from local regions around sensing locations to the global domain. The proposed method can enhance the CFD simulation results while preserving the overall original profile. An experiment in an air-conditioned room was implemented to verify the effectiveness of the proposed method. In the experiment, four sensor observations were used to calibrate a simulated thermal map with 167x365 data points. The experimental results show that the proposed method is effective and practical.

preprint2016arXiv

Photorealistic Facial Texture Inference Using Deep Neural Networks

We present a data-driven inference method that can synthesize a photorealistic texture map of a complete 3D face model given a partial 2D view of a person in the wild. After an initial estimation of shape and low-frequency albedo, we compute a high-frequency partial texture map, without the shading component, of the visible face area. To extract the fine appearance details from this incomplete input, we introduce a multi-scale detail analysis technique based on mid-layer feature correlations extracted from a deep convolutional neural network. We demonstrate that fitting a convex combination of feature correlations from a high-resolution face database can yield a semantically plausible facial detail description of the entire face. A complete and photorealistic texture map can then be synthesized by iteratively optimizing for the reconstructed feature correlations. Using these high-resolution textures and a commercial rendering framework, we can produce high-fidelity 3D renderings that are visually comparable to those obtained with state-of-the-art multi-view face capture systems. We demonstrate successful face reconstructions from a wide range of low resolution input images, includi

preprint2016arXiv

A Visual Representation for Editing Face Images

We propose a new approach for editing face images, which enables numerous exciting applications including face relighting, makeup transfer and face detail editing. Our face edits are based on a visual representation, which includes geometry, face segmentation, albedo, illumination and detail map. To recover our visual representation, we start by estimating geometry using a morphable face model, then decompose the face image to recover the albedo, and then shade the geometry with the albedo and illumination. The residual between our shaded geometry and the input image produces our detail map, which carries high frequency information that is either insufficiently or incorrectly captured by our shading process. By manipulating the detail map, we can edit face images with reality and identity preserved. Our representation allows various applications. First, it allows a user to directly manipulate various illumination. Second, it allows non-parametric makeup transfer with input face's distinctive identity features preserved. Third, it allows non-parametric modifications to the face appearance by transferring details. For face relighting and detail editing, we evaluate via a user stu

preprint2016arXiv

The Bricklayer Ecosystem - Art, Math, and Code

This paper describes the Bricklayer Ecosystem - a freely-available online educational ecosystem created for people of all ages and coding backgrounds. Bricklayer is designed in accordance with a "low-threshold infinite ceiling" philosophy and has been successfully used to teach coding to primary school students, middle school students, university freshmen, and in-service secondary math teachers. Bricklayer programs are written in the functional programming language SML and, when executed, create 2D and 3D artifacts. These artifacts can be viewed using a variety of third-party tools such as LEGO Digital Designer (LDD), LDraw, Minecraft clients, Brickr, as well as STereoLithography viewers.

preprint2016arXiv

FlyCap: Markerless Motion Capture Using Multiple Autonomous Flying Cameras

Aiming at automatic, convenient and non-instrusive motion capture, this paper presents a new generation markerless motion capture technique, the FlyCap system, to capture surface motions of moving characters using multiple autonomous flying cameras (autonomous unmanned aerial vehicles(UAV) each integrated with an RGBD video camera). During data capture, three cooperative flying cameras automatically track and follow the moving target who performs large scale motions in a wide space. We propose a novel non-rigid surface registration method to track and fuse the depth of the three flying cameras for surface motion tracking of the moving target, and simultaneously calculate the pose of each flying camera. We leverage the using of visual-odometry information provided by the UAV platform, and formulate the surface tracking problem in a non-linear objective function that can be linearized and effectively minimized through a Gaussian-Newton method. Quantitative and qualitative experimental results demonstrate the competent and plausible surface and motion reconstruction results

preprint2016arXiv

Navigable videos for presenting scientific data on head-mounted displays

Immersive, stereoscopic viewing enables scientists to better analyze the spatial structures of visualized physical phenomena. However, their findings cannot be properly presented in traditional media, which lack these core attributes. Creating a presentation tool that captures this environment poses unique challenges, namely related to poor viewing accessibility. Immersive scientific renderings often require high-end equipment, which can be impractical to obtain. We address these challenges with our authoring tool and navigational interface, which is designed for affordable head-mounted displays. With the authoring tool, scientists can show salient data features as connected 360° video paths, resulting in a "choose-your-own-adventure" experience. Our navigational interface features bidirectional video playback for added viewing control when users traverse the tailor-made content. We evaluate our system's benefits by authoring case studies on several data sets and conducting a usability study on the navigational interface's design. In summary, our approach provides scientists an immersive medium to visually present their research to the intended audience--spanning fr

preprint2014arXiv

Development & Implementation of a PyMOL 'putty' Representation

The PyMOL molecular graphics program has been modified to introduce a new 'putty' cartoon representation, akin to the 'sausage'-style representation of the MOLMOL molecular visualization (MolVis) software package. This document outlines the development and implementation of the putty representation.

preprint2016arXiv

Context Encoders: Feature Learning by Inpainting

We present an unsupervised visual feature learning algorithm driven by context-based pixel prediction. By analogy with auto-encoders, we propose Context Encoders -- a convolutional neural network trained to generate the contents of an arbitrary image region conditioned on its surroundings. In order to succeed at this task, context encoders need to both understand the content of the entire image, as well as produce a plausible hypothesis for the missing part(s). When training context encoders, we have experimented with both a standard pixel-wise reconstruction loss, as well as a reconstruction plus an adversarial loss. The latter produces much sharper results because it can better handle multiple modes in the output. We found that a context encoder learns a representation that captures not just appearance but also the semantics of visual structures. We quantitatively demonstrate the effectiveness of our learned features for CNN pre-training on classification, detection, and segmentation tasks. Furthermore, context encoders can be used for semantic inpainting tasks, either stand-alone or as initialization for non-parametric methods.

preprint2010arXiv

Graphic Symbol Recognition using Graph Based Signature and Bayesian Network Classifier

We present a new approach for recognition of complex graphic symbols in technical documents. Graphic symbol recognition is a well known challenge in the field of document image analysis and is at heart of most graphic recognition systems. Our method uses structural approach for symbol representation and statistical classifier for symbol recognition. In our system we represent symbols by their graph based signatures: a graphic symbol is vectorized and is converted to an attributed relational graph, which is used for computing a feature vector for the symbol. This signature corresponds to geometry and topology of the symbol. We learn a Bayesian network to encode joint probability distribution of symbol signatures and use it in a supervised learning scenario for graphic symbol recognition. We have evaluated our method on synthetically deformed and degraded images of pre-segmented 2D architectural and electronic symbols from GREC databases and have obtained encouraging recognition rates.

preprint2016arXiv

Oriented bounding boxes using multiresolution contours for fast interference detection of arbitrary geometry objects

Interference detection of arbitrary geometric objects is not a trivial task due to the heavy computational load imposed by implementation issues. The hierarchically structured bounding boxes help us to quickly isolate the contour of segments in interference. In this paper, a new approach is introduced to treat the interference detection problem involving the representation of arbitrary shaped objects. Our proposed method relies upon searching for the best possible way to represent contours by means of hierarchically structured rectangular oriented bounding boxes. This technique handles 2D objects boundaries defined by closed B-spline curves with roughness details. Each oriented box is adapted and fitted to the segments of the contour using second order statistical indicators from some elements of the segments of the object contour in a multiresolution framework. Our method is efficient and robust when it comes to 2D animations in real time. It can deal with smooth curves and polygonal approximations as well results are present to illustrate the performance of the new method.

preprint2016arXiv

Understanding and Exploiting Object Interaction Landscapes

Interactions play a key role in understanding objects and scenes, for both virtual and real world agents. We introduce a new general representation for proximal interactions among physical objects that is agnostic to the type of objects or interaction involved. The representation is based on tracking particles on one of the participating objects and then observing them with sensors appropriately placed in the interaction volume or on the interaction surfaces. We show how to factorize these interaction descriptors and project them into a particular participating object so as to obtain a new functional descriptor for that object, its interaction landscape, capturing its observed use in a spatio-temporal framework. Interaction landscapes are independent of the particular interaction and capture subtle dynamic effects in how objects move and behave when in functional use. Our method relates objects based on their function, establishes correspondences between shapes based on functional key points and regions, and retrieves peer and partner objects with respect to an interaction.

preprint2016arXiv

Fractal Art Generation using GPUs

Fractal image generation algorithms exhibit extreme parallelizability. Using general purpose graphics processing unit (GPU) programming to implement escape-time algorithms for Julia sets of functions,parallel methods generate visually attractive fractal images much faster than traditional methods. Vastly improved speeds are achieved using this method of computation, which allow real-time generation and display of images. A comparison is made between sequential and parallel implementations of the algorithm. An application created by the authors demonstrates using the increased speed to create dynamic imaging of fractals where the user may explore paths of parameter values corresponding to a given function's Mandelbrot set. Examples are given of artistic and mathematical insights gained by experiencing fractals interactively and from the ability to sample the parameter space quickly and comprehensively.

preprint2016arXiv

A Survey on 3D CAD model quality assurance and testing tools

A new taxonomy of issues related to CAD model quality is presented, which distinguishes between explicit and procedural models. For each type of model, morphologic, syntactic, and semantic errors are characterized. The taxonomy was validated successfully when used to classify quality testing tools, which are aimed at detecting and repairing data errors that may affect the simplification, interoperability, and reusability of CAD models. The study shows that low semantic level errors that hamper simplification are reasonably covered in explicit representations, although many CAD quality testers are still unaffordable for Small and Medium Enterprises, both in terms of cost and training time. Interoperability has been reasonably solved by standards like STEP AP 203 and AP214, but model reusability is not feasible in explicit representations. Procedural representations are promising, as interactive modeling editors automatically prevent most morphologic errors derived from unsuitable modeling strategies. Interoperability problems between procedural representations are expected to decrease dramatically with STEP AP242. Higher semantic aspects of quality such as assurance of design intent

preprint2016arXiv

Recent Advances in Transient Imaging: A Computer Graphics and Vision Perspective

Transient imaging has recently made a huge impact in the computer graphics and computer vision fields. By capturing, reconstructing, or simulating light transport at extreme temporal resolutions, researchers have proposed novel techniques to show movies of light in motion, see around corners, detect objects in highly-scattering media, or infer material properties from a distance, to name a few. The key idea is to leverage the wealth of information in the temporal domain at the pico or nanosecond resolution, information usually lost during the capture-time temporal integration. This paper presents recent advances in this field of transient imaging from a graphics and vision perspective, including capture techniques, analysis, applications and simulation.

preprint2016arXiv

Error-Bounded and Feature Preserving Surface Remeshing with Minimal Angle Improvement

The typical goal of surface remeshing consists in finding a mesh that is (1) geometrically faithful to the original geometry, (2) as coarse as possible to obtain a low-complexity representation and (3) free of bad elements that would hamper the desired application. In this paper, we design an algorithm to address all three optimization goals simultaneously. The user specifies desired bounds on approximation error δ, minimal interior angle θ and maximum mesh complexity N (number of vertices). Since such a desired mesh might not even exist, our optimization framework treats only the approximation error bound δ as a hard constraint and the other two criteria as optimization goals. More specifically, we iteratively perform carefully prioritized local operators, whenever they do not violate the approximation error bound and improve the mesh otherwise. In this way our optimization framework greedily searches for the coarsest mesh with minimal interior angle above θ and approximation error bounded by δ. Fast runtime is enabled by a local approximation error estimation, while implicit feature preservation is obtained by specifically designed vertex relocation operators. Experiments show th

preprint2016arXiv

Selecting the Best Quadrilateral Mesh for Given Planar Shape

The problem of mesh matching is addressed in this work. For a given n-sided planar region bounded by one loop of n polylines we are selecting optimal quadrilateral mesh from existing catalogue of meshes. The formulation of matching between planar shape and quadrilateral mesh from the catalogue is based on the problem of finding longest common subsequence (LCS). Theoretical foundation of mesh matching method is provided. Suggested method represents a viable technique for selecting best mesh for planar region and stepping stone for further parametrization of the region.

preprint2016arXiv

Simplification of Multi-Scale Geometry using Adaptive Curvature Fields

We present a novel algorithm to compute multi-scale curvature fields on triangle meshes. Our algorithm is based on finding robust mean curvatures using the ball neighborhood, where the radius of a ball corresponds to the scale of the features. The essential problem is to find a good radius for each ball to obtain a reliable curvature estimation. We propose an algorithm that finds suitable radii in an automatic way. In particular, our algorithm is applicable to meshes produced by image-based reconstruction systems. These meshes often contain geometric features at various scales, for example if certain regions have been captured in greater detail. We also show how such a multi-scale curvature field can be converted to a density field and used to guide applications like mesh simplification.

preprint2016arXiv

Deconfliction and Surface Generation from Bathymetry Data Using LR B-splines

A set of bathymetry point clouds acquired by different measurement techniques at different times, having different accuracy and varying patterns of points, are approximated by an LR B-spline surface. The aim is to represent the sea bottom with good accuracy and at the same time reduce the data size considerably. In this process the point clouds must be cleaned by selecting the "best" points for surface generation. This cleaning process is called deconfliction, and we use a rough approximation of the combined point clouds as a reference surface to select a consistent set of points. The reference surface is updated with the selected points to create an accurate approximation. LR B-splines is the selected surface format due to its suitability for adaptive refinement and approximation, and its ability to represent local detail without a global increase in the data size of the surface

356 works