xw-hu/Unveiling-Deep-Shadows
A Survey and Benchmark on Image and Video Shadow Detection, Removal, and Generation in the Era of Deep Learning (Awesome & Benchmark)
This project provides a comprehensive overview and benchmark for AI methods used in detecting, removing, and generating shadows in images and videos. It helps researchers and developers understand the performance of various models, comparing their accuracy, speed, and resource usage. By offering standardized evaluations and trained models, it allows practitioners to see what works best for different shadow-related challenges and integrate effective solutions into their own visual processing applications.
100 stars.
Use this if you are a researcher or developer working on computer vision tasks and need to identify, eliminate, or add shadows in images or videos, and want to compare state-of-the-art AI models.
Not ideal if you are an end-user looking for a ready-to-use application to fix shadows in your photos or videos without any development work.
Stars
100
Forks
3
Language
Python
License
—
Category
Last pushed
Feb 27, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/xw-hu/Unveiling-Deep-Shadows"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
cszn/KAIR
Image Restoration Toolbox (PyTorch). Training and testing codes for DPIR, USRNet, DnCNN, FFDNet,...
gabrieleilertsen/hdrcnn
HDR image reconstruction from a single exposure using deep CNNs
INVOKERer/DeepRFT
The code for 'Intriguing Findings of Frequency Selection for Image Deblurring' and 'Deep...
emidan19/deep-tempest
Restoration for TEMPEST images using deep-learning
VinAIResearch/blur-kernel-space-exploring
Exploring Image Deblurring via Blur Kernel Space (CVPR'21)