Statistics for topic image-restoration
RepositoryStats tracks 518,325 Github repositories, of these 122 are tagged with the image-restoration topic. The most common primary language for repositories using this topic is Python (90).
Stargazers over time for topic image-restoration
Most starred repositories for topic image-restoration (view more)
Trending repositories for topic image-restoration (view more)
GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.
Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
[ICLR 2024] Controlling Vision-Language Models for Universal Image Restoration. 5th place in the NTIRE 2024 Restore Any Image Model in the Wild Challenge.
SwinIR: Image Restoration Using Swin Transformer (official repository)
LYT-Net: Lightweight YUV Transformer-based Network for Low-Light Image Enhancement
[ICML2023] IRNeXt: Rethinking Convolutional Network Design for Image Restoration
neosr is a framework for training real-world single-image super-resolution networks.
[ICLR 2024] Controlling Vision-Language Models for Universal Image Restoration. 5th place in the NTIRE 2024 Restore Any Image Model in the Wild Challenge.
Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.
Bringing Old Photo Back to Life (CVPR 2020 oral)
The state-of-the-art image restoration model without nonlinear activation functions.
[ICML2023] IRNeXt: Rethinking Convolutional Network Design for Image Restoration
Collection of recent shadow removal works, including papers, codes, datasets, and metrics.
neosr is a framework for training real-world single-image super-resolution networks.
LYT-Net: Lightweight YUV Transformer-based Network for Low-Light Image Enhancement
A Collection of Low Level Vision Research Groups
Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.
Bringing Old Photo Back to Life (CVPR 2020 oral)
SwinIR: Image Restoration Using Swin Transformer (official repository)
"Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement" (ICCV 2023) & (NTIRE 2024 Challenge)
[CVPR 2024] Code for our Paper "CFAT: Unleashing Triangular Windows for Image Super-resolution"
[ICML2023] IRNeXt: Rethinking Convolutional Network Design for Image Restoration
Maximize Efficiency, Elevate Accuracy: Slash GPU Hours by Half with Efficient Pre-training!
LYT-Net: Lightweight YUV Transformer-based Network for Low-Light Image Enhancement
[IEEE TIP 2024] DEA-Net: Single image dehazing based on detail-enhanced convolution and content-guided attention
[ICLR 2024] Controlling Vision-Language Models for Universal Image Restoration. 5th place in the NTIRE 2024 Restore Any Image Model in the Wild Challenge.
"Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement" (ICCV 2023) & (NTIRE 2024 Challenge)
InstructIR: High-Quality Image Restoration Following Human Instructions https://huggingface.co/spaces/marcosv/InstructIR
[ICCV'23] Sparse Sampling Transformer with Uncertainty-Driven Ranking for Unified Removal of Raindrops and Rain Streaks
GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.
Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
Bringing Old Photo Back to Life (CVPR 2020 oral)
SwinIR: Image Restoration Using Swin Transformer (official repository)
The state-of-the-art image restoration model without nonlinear activation functions.
PromptIR: Prompting for All-in-One Blind Image Restoration [NeurIPS 2023]
"Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement" (ICCV 2023) & (NTIRE 2024 Challenge)
neosr is a framework for training real-world single-image super-resolution networks.
A Collection of Low Level Vision Research Groups
InstructIR: High-Quality Image Restoration Following Human Instructions https://huggingface.co/spaces/marcosv/InstructIR