Xiangyu Chen

Affiliations

University of Macau

papers

2,346

total citations

papers (19)

Activating More Pixels in Image Super-Resolution Transformer

CVPR 2023arXiv

929

citations

Combating Noisy Labels by Agreement: A Joint Training Method with Co-Regularization

CVPR 2020arXiv

643

citations

Train in Germany, Test in the USA: Making 3D Object Detectors Generalize

CVPR 2020arXiv

212

citations

Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research

NEURIPS 2023arXiv

163

citations

TAPE: Task-Agnostic Prior Embedding for Image Restoration

ECCV 2022arXiv

citations

A New Journey From SDRTV to HDRTV

ICCV 2021arXiv

citations

Ithaca365: Dataset and Driving Perception Under Repeated and Challenging Weather Conditions

CVPR 2022arXiv

citations

A Comparative Study of Image Restoration Networks for General Backbone Network Design

ECCV 2024arXiv

citations

Unifying Image Processing as Visual Prompting Question Answering

ICML 2024arXiv

citations

Under-Display Camera Image Restoration with Scattering Effect

ICCV 2023arXiv

citations

Effective Ambiguity Attack Against Passport-Based DNN Intellectual Property Protection Schemes Through Fully Connected Layer Substitution

CVPR 2023arXiv

citations

WeatherGFM: Learning a Weather Generalist Foundation Model via In-context Learning

ICLR 2025arXiv

citations

DiffVSR: Revealing an Effective Recipe for Taming Robust Video Super-Resolution Against Complex Degradations

ICCV 2025arXiv

citations

Controllable Distortion-Perception Tradeoff Through Latent Diffusion for Neural Image Compression

AAAI 2025arXiv

citations

Direction-Aware Video Demoiréing with Temporal-Guided Bilateral Learning

AAAI 2024

citations

Real-World Image Super-Resolution as Multi-Task Learning

NEURIPS 2023

citations

Xiangyu Chen

Affiliations

papers (19)

Activating More Pixels in Image Super-Resolution Transformer

Combating Noisy Labels by Agreement: A Joint Training Method with Co-Regularization

Train in Germany, Test in the USA: Making 3D Object Detectors Generalize

Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research

TAPE: Task-Agnostic Prior Embedding for Image Restoration

A New Journey From SDRTV to HDRTV

Ithaca365: Dataset and Driving Perception Under Repeated and Challenging Weather Conditions

A Comparative Study of Image Restoration Networks for General Backbone Network Design

Unifying Image Processing as Visual Prompting Question Answering

Under-Display Camera Image Restoration with Scattering Effect

Effective Ambiguity Attack Against Passport-Based DNN Intellectual Property Protection Schemes Through Fully Connected Layer Substitution

Image Demoireing in RAW and sRGB Domains

Reward Finetuning for Faster and More Accurate Unsupervised Object Discovery

SEAL: A Framework for Systematic Evaluation of Real-World Super-Resolution

WeatherGFM: Learning a Weather Generalist Foundation Model via In-context Learning

DiffVSR: Revealing an Effective Recipe for Taming Robust Video Super-Resolution Against Complex Degradations

Controllable Distortion-Perception Tradeoff Through Latent Diffusion for Neural Image Compression

Direction-Aware Video Demoiréing with Temporal-Guided Bilateral Learning

Real-World Image Super-Resolution as Multi-Task Learning

papers (19)

Activating More Pixels in Image Super-Resolution Transformer

Combating Noisy Labels by Agreement: A Joint Training Method with Co-Regularization

Train in Germany, Test in the USA: Making 3D Object Detectors Generalize

Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research

TAPE: Task-Agnostic Prior Embedding for Image Restoration

A New Journey From SDRTV to HDRTV

Ithaca365: Dataset and Driving Perception Under Repeated and Challenging Weather Conditions

A Comparative Study of Image Restoration Networks for General Backbone Network Design

Unifying Image Processing as Visual Prompting Question Answering

Under-Display Camera Image Restoration with Scattering Effect

Effective Ambiguity Attack Against Passport-Based DNN Intellectual Property Protection Schemes Through Fully Connected Layer Substitution

Image Demoireing in RAW and sRGB Domains

Reward Finetuning for Faster and More Accurate Unsupervised Object Discovery

SEAL: A Framework for Systematic Evaluation of Real-World Super-Resolution

WeatherGFM: Learning a Weather Generalist Foundation Model via In-context Learning

DiffVSR: Revealing an Effective Recipe for Taming Robust Video Super-Resolution Against Complex Degradations

Controllable Distortion-Perception Tradeoff Through Latent Diffusion for Neural Image Compression

Direction-Aware Video Demoiréing with Temporal-Guided Bilateral Learning

Real-World Image Super-Resolution as Multi-Task Learning