XingangPan/deep-generative-prior
Code for deep generative prior (ECCV2020 oral)
Leverages pretrained BigGAN as an image prior for diverse restoration and manipulation tasks—including colorization, inpainting, and super-resolution—via internal optimization without task-specific training. Uses PyTorch and supports distributed evaluation via SLURM, with class-conditional generation allowing both specified and random class sampling for flexible prior guidance.
516 stars. No commits in the last 6 months.
Stars
516
Forks
70
Language
Python
License
MIT
Category
Last pushed
Jul 04, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/XingangPan/deep-generative-prior"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
zhangyi-3/IDR
Self-Supervised Image Denoising via Iterative Data Refinement (CVPR2022)
yinboc/liif
Learning Continuous Image Representation with Local Implicit Image Function, in CVPR 2021 (Oral)
mv-lab/swin2sr
[ECCV] Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration. ...
eliahuhorwitz/DeepSIM
Official PyTorch implementation of the paper: "DeepSIM: Image Shape Manipulation from a Single...
cszn/FFDNet
FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising (TIP, 2018)