(CVPR 2022) Video Demoireing with Relation-Based Temporal Consistency

PyTorch implementation of VSR-Transformer

Handy image viewer based on PyQt5. Convenient for viewing and comparing :-)

Official repository of "BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment"

Blueprint Separable Residual Network for Efficient Image Super-Resolution

Image Restoration Toolbox (PyTorch). Training and testing codes for DPIR, USRNet, DnCNN, FFDNet, SRMD, DPSR, BSRGAN, SwinIR

TOFlow: Video Enhancement with Task-Oriented Flow

Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021, T-PAMI 2022

PyTorch implementation of "Reference-based Image Super-Resolution with Deformable Attention Transformer (ECCV2022)"

EFENet: Reference-based Video Super-Resolution with Enhanced Flow Estimation

[ICCV 2021 (Oral Presentation)] Dual-Camera Super-Resolution with Aligned Attention Modules (RefSR)

Winner of runtime track in NTIRE 2022 challenge on Efficient Super-Resolution

Code for C2-Matching (CVPR2021). Paper: Robust Reference-based Super-Resolution via C2-Matching.

[CVPR 2022] Official PyTorch Implementation for "Reference-based Video Super-Resolution Using Multi-Camera Video Triplets"

(ECCV2020 Workshops) Efficient Image Super-Resolution Using Pixel Attention.

The author's officially unofficial PyTorch BigGAN implementation.

MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Resolution (CVPR2021)

Temporally Consistent Video Colorization with Deep Feature Propagation and Self-regularization Learning

Official PyTorch Implementation of "GAN-Supervised Dense Visual Alignment" (CVPR 2022 Oral, Best Paper Finalist)

Unofficial implementation of Palette: Image-to-Image Diffusion Models by Pytorch

The source code of CVPR 2019 paper "Deep Exemplar-based Video Colorization".

Code for the paper "DeepRemaster: Temporal Source-Reference Attention Networks for Comprehensive Video Enhancement". http://iizuka.cs.tsukuba.ac.jp/projects/remastering/

Google Research

[CVPR'22 Oral] GMFlow: Learning Optical Flow via Global Matching

Dense matching library based on PyTorch

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

Official implementation of the paper GLU-Net (CVPR2020-Oral)

This repository implements the paper "Reference based Sketch Image Colorization using Augmented-Self Reference and Dense Semantic Correspondence" which is published in CVPR2020.

PyTorch implementation of CVPR 2020 paper (Reference-Based Sketch Image Colorization using Augmented-Self Reference and Dense Semantic Correspondence) and pre-trained model on ImageNet dataset