Wenhan Yang

41

Papers

286

Total Citations

Papers (41)

SinSR: Diffusion-Based Image Super-Resolution in a Single Step

Region-Adaptive Transform with Segmentation Prior for Image Compression

ColNeRF: Collaboration for Generalizable Sparse Input Neural Radiance Field

Backdoor Attacks Against No-Reference Image Quality Assessment Models via a Scalable Trigger

PRE-Mamba: A 4D State Space Model for Ultra-High-Frequent Event Camera Deraining

E3M: Zero-Shot Spatio-Temporal Video Grounding with Expectation-Maximization Multimodal Modulation

Mini-batch Coresets for Memory-efficient Language Model Training on Data Mixtures

Unified Coding for Both Human Perception and Generalized Machine Analytics with CLIP Supervision

Fast Omni-Directional Image Super-Resolution: Adapting the Implicit Image Function with Pixel and Semantic-Wise Spherical Geometric Priors

AFUNet: Cross-Iterative Alignment-Fusion Synergy for HDR Reconstruction via Deep Unfolding Paradigm

Purify Unlearnable Examples via Rate-Constrained Variational Autoencoders

Deep Joint Rain Detection and Removal From a Single Image

Attentive Generative Adversarial Network for Raindrop Removal From a Single Image

Erase or Fill? Deep Joint Recurrent Rain Removal and Reconstruction in Videos

Frame-Consistent Recurrent Video Deraining With Dual-Level Flow

From Fidelity to Perceptual Quality: A Semi-Supervised Approach for Low-Light Image Enhancement

Self-Learning Video Rain Streak Removal: When Cyclic Consistency Meets Temporal Correspondence

HLA-Face: Joint High-Low Adaptation for Low Light Face Detection

Self-Aligned Video Deraining With Transmission-Depth Consistency

Towards Robust Rain Removal Against Adversarial Attacks: A Comprehensive Benchmark Analysis and Beyond

Theoretical Insights in Model Inversion Robustness and Conditional Entropy Maximization for Collaborative Inference Systems

URetinex-Net: Retinex-Based Deep Unfolding Network for Low-Light Image Enhancement

MSDN: Mutually Semantic Distillation Network for Zero-Shot Learning

Raw Image Reconstruction With Learned Compact Metadata

Backdoor Attacks Against Deep Image Compression via Adaptive Frequency Trigger

ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removal

ExposureDiffusion: Learning to Expose for Low-light Image Enhancement

Boundary-Aware Divide and Conquer: A Diffusion-Based Solution for Unsupervised Shadow Removal

Similarity Min-Max: Zero-Shot Day-Night Domain Adaptation

Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects Suppression

Neural Data-Dependent Transform for Learned Image Compression

Cross-Granularity Online Optimization with Masked Compensated Information for Learned Image Compression

Adaptive Dual Uncertainty Optimization: Boosting Monocular 3D Object Detection under Test-Time Shifts

UP-Restorer: When Unrolling Meets Prompts for Unified Image Restoration

Seeing Dark Videos via Self-Learned Bottleneck Neural Representation

Local-Global Multi-Modal Distillation for Weakly-Supervised Temporal Video Grounding

Omnipotent Distillation with LLMs for Weakly-Supervised Natural Language Video Localization:

Misalignment-Robust Frequency Distribution Loss for Image Transformation

Correcting Diffusion-Based Perceptual Image Compression with Privileged End-to-End Decoder

Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor Attacks

Robust Contrastive Language-Image Pretraining against Data Poisoning and Backdoor Attacks