rozumden/DeFMO
[CVPR 2021] DeFMO: Deblurring and Shape Recovery of Fast Moving Objects
This project helps visual effects artists, forensic video analysts, or anyone working with video footage of fast-moving objects to restore clarity and detail. It takes blurry video or images of objects in motion and outputs sharper, deblurred versions with their true shapes recovered. The ideal users are professionals who need to analyze or enhance video content where motion blur obscures crucial information.
176 stars. No commits in the last 6 months.
Use this if you need to remove motion blur and reconstruct the original shape of objects that are moving rapidly in videos or still images.
Not ideal if your primary goal is to enhance static images or if you are dealing with blur caused by camera shake rather than object motion.
Stars
176
Forks
24
Language
Python
License
MIT
Category
Last pushed
Apr 06, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/rozumden/DeFMO"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
VITA-Group/DeblurGANv2
[ICCV 2019] "DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better" by Orest Kupyn,...
KupynOrest/DeblurGAN
Image Deblurring using Generative Adversarial Networks
ZhendongWang6/Uformer
[CVPR 2022] Official implementation of the paper "Uformer: A General U-Shaped Transformer for...
shuochsu/DeepVideoDeblurring
S. Su, M. Delbracio, J. Wang, G. Sapiro, W. Heidrich, O. Wang. Deep Video Deblurring. CVPR 2017,...
advimman/HiDT
Official repository for the paper "High-Resolution Daytime Translation Without Domain Labels"...