ICCV 2025: Frequency-Dynamic Attention Modulation for Dense Prediction

Spatially-Varying Autofocus

Automatic Video Generation from Scientific Papers

Source code for our paper "Transformer Meets Twicing: Harnessing Unattended Residual Information" [ICLR 2025].

Official repository of Polarity-aware Linear Attention for Vision Transformers (ICLR 2025)

[SIGGRAPH Asia 2025] Official code for "Bokeh Diffusion: Defocus Blur Control in Text-to-Image Diffusion Models."

Awesome Lists for Tenure-Track Assistant Professors and PhD students. (助理教授/博士生生存指南)

MulimgViewer is a multi-image viewer that can open multiple images in one interface, which is convenient for image comparison and image stitching.

[CVPR'2025] URWKV: Unified RWKV Model with Multi-state Perspective for Low-light Image Restoration

You can easily calculate FVD, PSNR, SSIM, LPIPS for evaluating the quality of generated or predicted videos.

Monitor Google Scholar author citation counts and track changes automatically without opening tabs.

The official implementation of "An Efficient and Mixed Heterogeneous Model for Image Restoration"

MDT

Spark-TTS Inference Code

Unpaired Image Dehazing via Kolmogorov-Arnold Transformation

Superpixel Attention Paper

[ECCV 2024] QueryCDR: Query-based Controllable Distortion Rectification Network for Fisheye Images

[BMVC'24] A Super-pixel-based Approach to the Stable Interpretation of Neural Networks

[ICCV 2025] FoundIR: Unleashing Million-scale Training Data to Advance Foundation Models for Image Restoration

Superpixel Tokenization for Vision Transformers: Preserving Semantic Integrity in Visual Tokens

Implementation for MomentumSMoE

MoH: Multi-Head Attention as Mixture-of-Head Attention

Official implementation of ICCV2023 "Towards Real-World Burst Image Super-Resolution: Benchmark and Method"