Awesome-Deblurring
Restormer
Awesome-Deblurring | Restormer | |
---|---|---|
7 | 3 | |
2,276 | 1,554 | |
- | - | |
6.3 | 3.8 | |
12 days ago | 27 days ago | |
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.
Awesome-Deblurring
-
Can someone help me? Hit and run
This is a really tough one. I'm new to this and haven't made any progress after an hour. Here are some resources though: https://github.com/subeeshvasu/Awesome-Deblurring
- Think my gf of 8 years cheated - can anyone make the text In the cropped picture readable
-
Removing blur from images – deconvolution and using simple image filters
This is an ongoing area of study. Here's a list of research (ML-focused) on the topic - https://github.com/subeeshvasu/Awesome-Deblurring
I personally used a technique (based on a paper from that list) that learns a kernel based on the idea that it's easier to learn a latent source image and a blur compared to learning a blurred image.
- When the protest is by bike the medics have to be creative
- protect protester identities
-
Capture License plate of racist banana peel thrower from 4k video?
Could be some new hotness can get it done, but the real answer here is probably to record a video with a better angle, and closer. Maybe there's some way to hide the hardware so that it's not super obvious there's a camera.
-
GDPR tool for video -> Found a tool that can blur faces in video exports... Lifesaver when the police requires data from my CCTV.
Does this remove enough information so the original faces can not be reconstructed (eg.: with some de-blur magic)? The blur is different in every frame, I suspect more information can be reconstructed because of that. Maybe pixelization or filling with a single color is a better solution.
Restormer
-
[R] Restormer: Efficient Transformer for High-Resolution Image Restoration (CVPR2022--ORAL) + Colab Demo + Gradio Web Demo
Code for https://arxiv.org/abs/2111.09881 found: https://github.com/swz30/Restormer
- Restormer: Efficient Transformer for High-Resolution Image Restoration
What are some alternatives?
machine-learning-for-software-engineers - A complete daily plan for studying to become a machine learning engineer.
SwinIR - SwinIR: Image Restoration Using Swin Transformer (official repository)
awesome-deep-learning - A curated list of awesome Deep Learning tutorials, projects and communities.
maxim-pytorch - [CVPR 2022 Oral] PyTorch re-implementation for "MAXIM: Multi-Axis MLP for Image Processing", with *training code*. Official Jax repo: https://github.com/google-research/maxim
DeFMO - [CVPR 2021] DeFMO: Deblurring and Shape Recovery of Fast Moving Objects
NAFNet - The state-of-the-art image restoration model without nonlinear activation functions.
HRNet-Semantic-Segmentation - The OCR approach is rephrased as Segmentation Transformer: https://arxiv.org/abs/1909.11065. This is an official implementation of semantic segmentation for HRNet. https://arxiv.org/abs/1908.07919
transfiner - Mask Transfiner for High-Quality Instance Segmentation, CVPR 2022
MPRNet - [CVPR 2021] Multi-Stage Progressive Image Restoration. SOTA results for Image deblurring, deraining, and denoising.
DirectVoxGO - Direct voxel grid optimization for fast radiance field reconstruction.
maxim - [CVPR 2022 Oral] Official repository for "MAXIM: Multi-Axis MLP for Image Processing". SOTA for denoising, deblurring, deraining, dehazing, and enhancement.
PatchFusion - [CVPR 2024] An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth Estimation