onpix/LCDPNet
Official PyTorch code and dataset of the paper "Local Color Distributions Prior for Image Enhancement" [ECCV2022]
This project helps photographers and digital artists fix images that suffer from both overly bright (over-exposed) and overly dark (under-exposed) areas simultaneously. It takes an image with these mixed exposure issues and outputs a single, balanced image where details in both highlights and shadows are recovered. This tool is for anyone working with photos that have challenging lighting conditions.
172 stars. No commits in the last 6 months.
Use this if you have photographs with mixed lighting conditions, where some parts are washed out and others are too dim, and you need to correct both issues in one go.
Not ideal if your images only have a single exposure problem (e.g., entirely too dark or entirely too bright) as other tools might be more straightforward for those specific cases.
Stars
172
Forks
15
Language
Python
License
MIT
Category
Last pushed
Jul 21, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/onpix/LCDPNet"
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"...