[CVPR 2025] 3DEnhancer: Consistent Multi-View Diffusion for 3D Enhancement

ObjectClear: Complete Object Removal via Object-Effect Attention

RetinaFace: Deep Face Detection Library for Python

Quick scripts to calculate CLIP text-image similarity

[ECCV 2022] LEDNet: Joint Low-light Enhancement and Deblurring in the Dark

High-resolution models for human tasks.

Halpe: full body human pose estimation and human-object interaction detection dataset

Official implementation of S3Diff

Deep learning in motion deblurring: current status, benchmarks and future prospects[J], The Visual Computer, 2024.

[NeurIPS 2024] Generalizable Implicit Motion Modeling for Video Frame Interpolation

Fast and differentiable MS-SSIM and SSIM for pytorch.

[CVPR2024] SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution

A Novel Linear Array Pushbroom (LAP) Image Restoration Method. (Accepted by AAAI 2024)

Lossless Training Speed Up by Unbiased Dynamic Data Pruning

[CVPR 2023] Efficient Frequency Domain-based Transformer for High-Quality Image Deblurring

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

ProRes: Exploring Degradation-aware Visual Prompt for Universal Image Restoration

Code and models for the paper "One Transformer Fits All Distributions in Multi-Modal Diffusion"

Speed up Stable Diffusion with this one simple trick!

End-to-End Object Detection with Transformers

Relate Anything Model is capable of taking an image as input and utilizing SAM to identify the corresponding mask within the image.