NAFNet
FBCNN
Our great sponsors
NAFNet | FBCNN | |
---|---|---|
5 | 4 | |
1,992 | 391 | |
5.1% | - | |
0.0 | 0.0 | |
27 days ago | 5 days ago | |
Python | Python | |
GNU General Public License v3.0 or later | Apache License 2.0 |
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
FBCNN
-
January 2022 Tsukasa (Cleaned + Deartifacted Version)
JPEG deartifacting done via https://github.com/jiaxi-jiang/FBCNN.
- Digimon - genérico PT 4K
-
JPEG Compression Artifacts Removal AI - FBCNN
Some of the sample images look fine but others look absolutely terrible. Especially the blue-tinted one (a still from a movie?) where the filter erases most of the fine detail. The man's face is so smooth that it's creepy. In the Tom and Jerry image, Jerry (the mouse)'s whiskers almost disappear where they overlap his face, and the drawer he's standing on loses most detail. If you can't see it in the video then look at the same images in full resolution on the GitHub page.
What are some alternatives?
MPRNet - [CVPR 2021] Multi-Stage Progressive Image Restoration. SOTA results for Image deblurring, deraining, and denoising.
EasyOCR - Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
Real-ESRGAN-colab - A Real-ESRGAN model trained on a custom dataset
XMem - [ECCV 2022] XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
AgentFormer - [ICCV 2021] Official PyTorch Implementation of "AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting".
DeblurGANv2 - [ICCV 2019] "DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better" by Orest Kupyn, Tetiana Martyniuk, Junru Wu, Zhangyang Wang
Robo-Semantic-Segmentation - Just a simple semantic segmentation library that I developed to speed up the image segmentation pipeline
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.