advimman/HiDT
Official repository for the paper "High-Resolution Daytime Translation Without Domain Labels" (CVPR2020, Oral)
Enables unsupervised image-to-image translation for daytime scenes and artistic style transfer using a dual-generator architecture with optional enhancement upsampling, requiring no paired domain labels. Implements fully convolutional inference modes for arbitrary resolution processing, with separate pretrained models for photorealistic (daytime) and artistic (WikiArt) domains. Built in PyTorch with inference-only code and Colab notebook support for quick experimentation.
652 stars. No commits in the last 6 months.
Stars
652
Forks
87
Language
Jupyter Notebook
License
BSD-3-Clause
Category
Last pushed
Feb 15, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/advimman/HiDT"
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...
codeslake/IFAN
[CVPR 2021] Official PyTorch Implementation for "Iterative Filter Adaptive Network for Single...