Algolzw/daclip-uir
[ICLR 2024] Controlling Vision-Language Models for Universal Image Restoration. 5th place in the NTIRE 2024 Restore Any Image Model in the Wild Challenge.
Leverages CLIP's vision-language representations with degradation-aware control to enable unified handling of 10+ image degradation types (blur, haze, noise, rain, etc.) within a single model. Uses a diffusion-based restoration backbone (SDE framework) guided by CLIP embeddings, with posterior sampling for improved photo-realistic generation, and supports both synthetic and real-world mixed degradations through specialized model variants.
807 stars. No commits in the last 6 months.
Stars
807
Forks
51
Language
Python
License
MIT
Category
Last pushed
Aug 07, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Algolzw/daclip-uir"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
KupynOrest/DeblurGAN
Image Deblurring using Generative Adversarial Networks
VITA-Group/DeblurGANv2
[ICCV 2019] "DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better" by Orest Kupyn,...
shuochsu/DeepVideoDeblurring
S. Su, M. Delbracio, J. Wang, G. Sapiro, W. Heidrich, O. Wang. Deep Video Deblurring. CVPR 2017,...
ZhendongWang6/Uformer
[CVPR 2022] Official implementation of the paper "Uformer: A General U-Shaped Transformer for...
advimman/HiDT
Official repository for the paper "High-Resolution Daytime Translation Without Domain Labels"...