Shuhang Gu

36

Papers

100

Total Citations

Papers (36)

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

Uncertainty-guided Perturbation for Image Super-Resolution Diffusion Model

Robust Message Embedding via Attention Flow-Based Steganography

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

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

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

Stereo Risk: A Continuous Modeling Approach to Stereo Matching

Discriminative Learning of Iteration-Wise Priors for Blind Deconvolution

Multispectral Images Denoising by Intrinsic Tensor Sparsity Regularization

Dictionary Pair Classifier Driven Convolutional Neural Networks for Object Detection

Learning Dynamic Guidance for Depth Image Enhancement

Learning Deep CNN Denoiser Prior for Image Restoration

Learning Convolutional Networks for Content-Weighted Image Compression

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

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

The Heterogeneity Hypothesis: Finding Layer-Wise Differentiated Network Architectures

Revisiting Random Channel Pruning for Neural Network Compression

Single Image Depth Prediction Made Better: A Multivariate Gaussian Take

Convolutional Sparse Coding for Image Super-Resolution

Joint Convolutional Analysis and Synthesis Sparse Representation for Single Image Layer Separation

Self-Guided Network for Fast Image Denoising

Fast Image Restoration With Multi-Bin Trainable Linear Units

Learning Filter Basis for Convolutional Neural Network Compression

Improving Deep Video Compression by Resolution-adaptive Flow Coding

DHP: Differentiable Meta Pruning via HyperNetworks

Video Super-Resolution with Recurrent Structure-Detail Network

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

Video Rain Streak Removal by Multiscale Convolutional Sparse Coding

Progressive Focused Transformer for Single Image Super-Resolution

Learned Image Compression with Dictionary-based Entropy Model

Consistency Trajectory Matching for One-Step Generative Super-Resolution

Improved Implicit Neural Representation with Fourier Reparameterized Training

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

Learning Motion Refinement for Unsupervised Face Animation