Shuhang Gu

papers

1,389

total citations

papers (24)

Video Super-Resolution with Recurrent Structure-Detail Network

ECCV 2020arXiv

248

citations

Group Sparsity: The Hinge Between Filter Pruning and Decomposition for Network Compression

CVPR 2020arXiv

208

citations

Flow-Based Kernel Prior With Application to Blind Super-Resolution

CVPR 2021arXiv

149

citations

Unsupervised Real-World Image Super Resolution via Domain-Distance Aware Training

CVPR 2021arXiv

148

citations

Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary

CVPR 2024arXiv

citations

Video Super-Resolution Transformer with Masked Inter&Intra-Frame Attention

CVPR 2024arXiv

citations

Improved Implicit Neural Representation with Fourier Reparameterized Training

CVPR 2024arXiv

citations

The Heterogeneity Hypothesis: Finding Layer-Wise Differentiated Network Architectures

CVPR 2021arXiv

citations

Single Image Depth Prediction Made Better: A Multivariate Gaussian Take

CVPR 2023arXiv

citations

Uncertainty-guided Perturbation for Image Super-Resolution Diffusion Model

CVPR 2025arXiv

citations

Learned Image Compression with Dictionary-based Entropy Model

CVPR 2025arXiv

citations

Progressive Focused Transformer for Single Image Super-Resolution

CVPR 2025arXiv

citations

Learning Motion Refinement for Unsupervised Face Animation

NEURIPS 2023arXiv

citations

Stereo Risk: A Continuous Modeling Approach to Stereo Matching

ICML 2024arXiv

citations

Robust Message Embedding via Attention Flow-Based Steganography

CVPR 2025arXiv

citations

PerLDiff: Controllable Street View Synthesis Using Perspective-Layout Diffusion Model

ICCV 2025arXiv

citations

Consistency Trajectory Matching for One-Step Generative Super-Resolution

ICCV 2025arXiv

citations

GeoDepth: From Point-to-Depth to Plane-to-Depth Modeling for Self-Supervised Monocular Depth Estimation

CVPR 2025

citations

Learning Pixel-adaptive Multi-layer Perceptrons for Real-time Image Enhancement

ICCV 2025arXiv

citations

"Restore Globally, Refine Locally: A Mask-Guided Scheme to Accelerate Super-Resolution Networks"

ECCV 2022

citations

Multi-Domain Learning for Accurate and Few-Shot Color Constancy

CVPR 2020

citations

Shuhang Gu

papers (24)

Video Super-Resolution with Recurrent Structure-Detail Network

Group Sparsity: The Hinge Between Filter Pruning and Decomposition for Network Compression

Flow-Based Kernel Prior With Application to Blind Super-Resolution

Unsupervised Real-World Image Super Resolution via Domain-Distance Aware Training

Improving Deep Video Compression by Resolution-adaptive Flow Coding

DHP: Differentiable Meta Pruning via HyperNetworks

Revisiting Random Channel Pruning for Neural Network Compression

Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary

Video Super-Resolution Transformer with Masked Inter&Intra-Frame Attention

Improved Implicit Neural Representation with Fourier Reparameterized Training

The Heterogeneity Hypothesis: Finding Layer-Wise Differentiated Network Architectures

Single Image Depth Prediction Made Better: A Multivariate Gaussian Take

Uncertainty-guided Perturbation for Image Super-Resolution Diffusion Model

Learned Image Compression with Dictionary-based Entropy Model

Progressive Focused Transformer for Single Image Super-Resolution

Learning Motion Refinement for Unsupervised Face Animation

Stereo Risk: A Continuous Modeling Approach to Stereo Matching

Robust Message Embedding via Attention Flow-Based Steganography

PerLDiff: Controllable Street View Synthesis Using Perspective-Layout Diffusion Model

Consistency Trajectory Matching for One-Step Generative Super-Resolution

GeoDepth: From Point-to-Depth to Plane-to-Depth Modeling for Self-Supervised Monocular Depth Estimation

Learning Pixel-adaptive Multi-layer Perceptrons for Real-time Image Enhancement

"Restore Globally, Refine Locally: A Mask-Guided Scheme to Accelerate Super-Resolution Networks"

Multi-Domain Learning for Accurate and Few-Shot Color Constancy

papers (24)

Video Super-Resolution with Recurrent Structure-Detail Network

Group Sparsity: The Hinge Between Filter Pruning and Decomposition for Network Compression

Flow-Based Kernel Prior With Application to Blind Super-Resolution

Unsupervised Real-World Image Super Resolution via Domain-Distance Aware Training

Improving Deep Video Compression by Resolution-adaptive Flow Coding

DHP: Differentiable Meta Pruning via HyperNetworks

Revisiting Random Channel Pruning for Neural Network Compression

Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary

Video Super-Resolution Transformer with Masked Inter&Intra-Frame Attention

Improved Implicit Neural Representation with Fourier Reparameterized Training

The Heterogeneity Hypothesis: Finding Layer-Wise Differentiated Network Architectures

Single Image Depth Prediction Made Better: A Multivariate Gaussian Take

Uncertainty-guided Perturbation for Image Super-Resolution Diffusion Model

Learned Image Compression with Dictionary-based Entropy Model

Progressive Focused Transformer for Single Image Super-Resolution

Learning Motion Refinement for Unsupervised Face Animation

Stereo Risk: A Continuous Modeling Approach to Stereo Matching

Robust Message Embedding via Attention Flow-Based Steganography

PerLDiff: Controllable Street View Synthesis Using Perspective-Layout Diffusion Model

Consistency Trajectory Matching for One-Step Generative Super-Resolution

GeoDepth: From Point-to-Depth to Plane-to-Depth Modeling for Self-Supervised Monocular Depth Estimation

Learning Pixel-adaptive Multi-layer Perceptrons for Real-time Image Enhancement

"Restore Globally, Refine Locally: A Mask-Guided Scheme to Accelerate Super-Resolution Networks"

Multi-Domain Learning for Accurate and Few-Shot Color Constancy