advimman/HiDT
Official repository for the paper "High-Resolution Daytime Translation Without Domain Labels" (CVPR2020, Oral)
This tool transforms images from one visual style to another, specifically excelling at changing the 'time of day' feel of a photo (e.g., making a daytime scene look like night) or applying artistic styles. You provide an input image and a 'style' image, and it generates a new image where your input content is rendered in the style of the other. This is useful for graphic designers, artists, or anyone working with visual content who needs to quickly re-imagine images.
652 stars. No commits in the last 6 months.
Use this if you need to stylize existing images, change their apparent lighting conditions, or apply artistic textures without manually editing each one.
Not ideal if you need precise object manipulation or pixel-level control over your image transformations, as this focuses on broader stylistic changes.
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
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,...
mahmoudnafifi/Exposure_Correction
Project page of the paper "Learning Multi-Scale Photo Exposure Correction" (CVPR 2021).