NAFNet
Real-ESRGAN-colab
| NAFNet | Real-ESRGAN-colab | |
|---|---|---|
| 5 | 1 | |
| 2,002 | 44 | |
| 2.5% | - | |
| 0.0 | 0.0 | |
| 12 days ago | over 1 year ago | |
| Python | Python | |
| GNU General Public License v3.0 or later | - |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
NAFNet
-
Workflow to denoise low quality images?
I've tried using NAFNet but this simply does not work on most images I've tried. I've tried using VEAencode then using low denoise parameter on a KSampler while describing the image as much as possible and did not get good results as well.
- Best AI models for image resolution upscaling?
-
Denoising image gives corrupted result
I am currently trying out different denoising techniques, and processed my dataset using NAFNet's Denoising model. However, I am getting a corrupted image as a result when processing certain ones. Down below is an example. Does anyone have an explanation for this?
- NAFNet: Nonlinear Activation Free Network for Image Restoration
Real-ESRGAN-colab
-
Retrained Real-ESRGAN version used by ruDALL-E (a text-to-image AI) may be of interest
I noticed that the 256x256 -> 1024x1024 upscalings used by the ruDALL-E (text-to-image AI) demo site looked more detailed than other upscalers I've used. It apparently uses a retrained Real-ESRGAN. Here is a comparison I did of 2 synthetic images upscaled with this and 2 other upscalers. The GitHub repos are here and here. A web app version is here.
What are some alternatives?
MPRNet - [CVPR 2021] Multi-Stage Progressive Image Restoration. SOTA results for Image deblurring, deraining, and denoising.
Real-ESRGAN - Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
XMem - [ECCV 2022] XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
BasicSR - Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, BasicVSR, SwinIR, ECBSR, etc. Also support StyleGAN2, DFDNet.
DeblurGANv2 - [ICCV 2019] "DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better" by Orest Kupyn, Tetiana Martyniuk, Junru Wu, Zhangyang Wang
Real-ESRGAN - PyTorch implementation of Real-ESRGAN model
Restormer - [CVPR 2022--Oral] Restormer: Efficient Transformer for High-Resolution Image Restoration. SOTA for motion deblurring, image deraining, denoising (Gaussian/real data), and defocus deblurring.
traiNNer - traiNNer: Deep learning framework for image and video super-resolution, restoration and image-to-image translation, for training and testing.
FBCNN - Official Code for ICCV 2021 paper "Towards Flexible Blind JPEG Artifacts Removal (FBCNN)"
Real-ESRGAN-Video-Batch-Process - Upscale any number of videos using this colab notebook!
Image-Super-Resolution-via-Iterative-Refinement - Unofficial implementation of Image Super-Resolution via Iterative Refinement by Pytorch
mmagic - OpenMMLab Multimodal Advanced, Generative, and Intelligent Creation Toolbox. Unlock the magic 🪄: Generative-AI (AIGC), easy-to-use APIs, awsome model zoo, diffusion models, for text-to-image generation, image/video restoration/enhancement, etc.