BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Gang He

Gang He contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Computer Visioneess.IVMultimediaArtificial IntelligenceComputation and Language

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
6works
0followers
5topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

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

Published work

6 published item(s)

preprint2026arXiv

Allegory of the Cave: Measurement-Grounded Vision-Language Learning

Vision-language models typically reason over post-ISP RGB images, although RGB rendering can clip, suppress, or quantize sensor evidence before inference. We study whether grounding improves when the visual interface is moved closer to the underlying camera measurement. We formulate measurement-grounded vision-language learning and instantiate it as PRISM-VL, which combines RAW-derived Meas.-XYZ inputs, camera-conditioned grounding, and Exposure-Bracketed Supervision Aggregation for transferring supervision from RGB proxies to measurement-domain observations. Using a quality-controlled 150K instruction-tuning set and a held-out benchmark targeting low-light, HDR, visibility-sensitive, and hallucination-sensitive cases, PRISM-VL-8B reaches 0.6120 BLEU, 0.4571 ROUGE-L, and 82.66\% LLM-Judge accuracy, improving over the RGB Qwen3-VL-8B baseline by +0.1074 BLEU, +0.1071 ROUGE-L, and +4.46 percentage points. These results suggest that part of VLM grounding error arises from information lost during RGB rendering, and that preserving measurement-domain evidence can improve multimodal reasoning.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Beyond Feature Mapping GAP: Integrating Real HDRTV Priors for Superior SDRTV-to-HDRTV Conversion

The rise of HDR-WCG display devices has highlighted the need to convert SDRTV to HDRTV, as most video sources are still in SDR. Existing methods primarily focus on designing neural networks to learn a single-style mapping from SDRTV to HDRTV. However, the limited information in SDRTV and the diversity of styles in real-world conversions render this process an ill-posed problem, thereby constraining the performance and generalization of these methods. Inspired by generative approaches, we propose a novel method for SDRTV to HDRTV conversion guided by real HDRTV priors. Despite the limited information in SDRTV, introducing real HDRTV as reference priors significantly constrains the solution space of the originally high-dimensional ill-posed problem. This shift transforms the task from solving an unreferenced prediction problem to making a referenced selection, thereby markedly enhancing the accuracy and reliability of the conversion process. Specifically, our approach comprises two stages: the first stage employs a Vector Quantized Generative Adversarial Network to capture HDRTV priors, while the second stage matches these priors to the input SDRTV content to recover realistic HDRTV outputs. We evaluate our method on public datasets, demonstrating its effectiveness with significant improvements in both objective and subjective metrics across real and synthetic datasets.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Hard-sample Guided Hybrid Contrast Learning for Unsupervised Person Re-Identification

Unsupervised person re-identification (Re-ID) is a promising and very challenging research problem in computer vision. Learning robust and discriminative features with unlabeled data is of central importance to Re-ID. Recently, more attention has been paid to unsupervised Re-ID algorithms based on clustered pseudo-label. However, the previous approaches did not fully exploit information of hard samples, simply using cluster centroid or all instances for contrastive learning. In this paper, we propose a Hard-sample Guided Hybrid Contrast Learning (HHCL) approach combining cluster-level loss with instance-level loss for unsupervised person Re-ID. Our approach applies cluster centroid contrastive loss to ensure that the network is updated in a more stable way. Meanwhile, introduction of a hard instance contrastive loss further mines the discriminative information. Extensive experiments on two popular large-scale Re-ID benchmarks demonstrate that our HHCL outperforms previous state-of-the-art methods and significantly improves the performance of unsupervised person Re-ID. The code of our work is available soon at https://github.com/bupt-ai-cz/HHCL-ReID.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

NTIRE 2022 Challenge on High Dynamic Range Imaging: Methods and Results

This paper reviews the challenge on constrained high dynamic range (HDR) imaging that was part of the New Trends in Image Restoration and Enhancement (NTIRE) workshop, held in conjunction with CVPR 2022. This manuscript focuses on the competition set-up, datasets, the proposed methods and their results. The challenge aims at estimating an HDR image from multiple respective low dynamic range (LDR) observations, which might suffer from under- or over-exposed regions and different sources of noise. The challenge is composed of two tracks with an emphasis on fidelity and complexity constraints: In Track 1, participants are asked to optimize objective fidelity scores while imposing a low-complexity constraint (i.e. solutions can not exceed a given number of operations). In Track 2, participants are asked to minimize the complexity of their solutions while imposing a constraint on fidelity scores (i.e. solutions are required to obtain a higher fidelity score than the prescribed baseline). Both tracks use the same data and metrics: Fidelity is measured by means of PSNR with respect to a ground-truth HDR image (computed both directly and with a canonical tonemapping operation), while complexity metrics include the number of Multiply-Accumulate (MAC) operations and runtime (in seconds).

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

SDRTV-to-HDRTV via Hierarchical Dynamic Context Feature Mapping

In this work, we address the task of SDR videos to HDR videos(SDRTV-to-HDRTV). Previous approaches use global feature modulation for SDRTV-to-HDRTV. Feature modulation scales and shifts the features in the original feature space, which has limited mapping capability. In addition, the global image mapping cannot restore detail in HDR frames due to the luminance differences in different regions of SDR frames. To resolve the appeal, we propose a two-stage solution. The first stage is a hierarchical Dynamic Context feature mapping (HDCFM) model. HDCFM learns the SDR frame to HDR frame mapping function via hierarchical feature modulation (HME and HM ) module and a dynamic context feature transformation (DCT) module. The HME estimates the feature modulation vector, HM is capable of hierarchical feature modulation, consisting of global feature modulation in series with local feature modulation, and is capable of adaptive mapping of local image features. The DCT module constructs a feature transformation module in conjunction with the context, which is capable of adaptively generating a feature transformation matrix for feature mapping. Compared with simple feature scaling and shifting, the DCT module can map features into a new feature space and thus has a more excellent feature mapping capability. In the second stage, we introduce a patch discriminator-based context generation model PDCG to obtain subjective quality enhancement of over-exposed regions. PDCG can solve the problem that the model is challenging to train due to the proportion of overexposed regions of the image. The proposed method can achieve state-of-the-art objective and subjective quality results. Specifically, HDCFM achieves a PSNR gain of 0.81 dB at a parameter of about 100K. The number of parameters is 1/14th of the previous state-of-the-art methods. The test code will be released soon.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

RR-DnCNN v2.0: Enhanced Restoration-Reconstruction Deep Neural Network for Down-Sampling Based Video Coding

Integrating deep learning techniques into the video coding framework gains significant improvement compared to the standard compression techniques, especially applying super-resolution (up-sampling) to down-sampling based video coding as post-processing. However, besides up-sampling degradation, the various artifacts brought from compression make super-resolution problem more difficult to solve. The straightforward solution is to integrate the artifact removal techniques before super-resolution. However, some helpful features may be removed together, degrading the super-resolution performance. To address this problem, we proposed an end-to-end restoration-reconstruction deep neural network (RR-DnCNN) using the degradation-aware technique, which entirely solves degradation from compression and sub-sampling. Besides, we proved that the compression degradation produced by Random Access configuration is rich enough to cover other degradation types, such as Low Delay P and All Intra, for training. Since the straightforward network RR-DnCNN with many layers as a chain has poor learning capability suffering from the gradient vanishing problem, we redesign the network architecture to let reconstruction leverages the captured features from restoration using up-sampling skip connections. Our novel architecture is called restoration-reconstruction u-shaped deep neural network (RR-DnCNN v2.0). As a result, our RR-DnCNN v2.0 outperforms the previous works and can attain 17.02% BD-rate reduction on UHD resolution for all-intra anchored by the standard H.265/HEVC. The source code is available at https://minhmanho.github.io/rrdncnn/.

0 citations0 reviewsNo code linkedOpen access