Pytorch Code for the paper TransWeather - CVPR 2022

Code for "Restoring Vision in Adverse Weather Conditions with Patch-Based Denoising Diffusion Models" [TPAMI 2023]

[CVPR 2022] Learning Multiple Adverse Weather Removal via Two-stage Knowledge Learning and Multi-contrastive Regularization: Toward a Unified Model

This is the source code of PMS-Net: Robust Haze Removal Based on Patch Map for Single Images which has been published in CVPR 2019 Long Beach

This is the source code of PMHLD-Patch-Map-Based-Hybrid-Learning-DehazeNet-for-Single-Image-Haze-Removal which has been accepted by IEEE Transaction on Image Processing 2020.

[ECCV 2024] Histoformer: Restoring Images in Adverse Weather Conditions via Histogram Transformer

This is the project page of our paper which has been published in ECCV 2020.

Code for Blind Image Decomposition (BID) and Blind Image Decomposition network (BIDeN). ECCV, 2022.

This paper is accepted by ICCV 2021.

[ECCV 2024] OneRestore: A Universal Restoration Framework for Composite Degradation

[ NeurIPS 2024 ] The official PyTorch implementation for Learning Truncated Causal History Model for Video Restoration.

Inference code for "Unified Multi-Weather Transformer for Multi-Weather Image Restoration".

[ICCV 2023] Snow Removal in Video: A New Dataset and A Novel Method

This paper is accepted by IEEE TCSVT

[ECCV‘24] Teaching Tailored to Talent: Adverse Weather Restoration via Prompt Pool and Depth-Anything Constraint

The official code of the IEEE Access paper "Multiple Adverse Weather Removal Using Masked-Based Pre-Training and Dual-Pooling Adaptive Convolution (MPDAC)"

Towards Real-World Adverse Weather Image Restoration: Enhancing Clearness and Semantics with Vision-Language Models (ECCV 2024)