compphoto/IntrinsicHDR
Repo for the paper "Intrinsic Single-Image HDR Reconstruction" (ECCV 2024)
This project helps photographers and digital artists transform standard photos into stunning high-dynamic-range (HDR) images, even if only a single photo is available. It takes a regular, low-dynamic-range (LDR) image as input and outputs a high-quality HDR image, revealing rich details and colors lost in overly bright or dark areas. It's ideal for anyone working with digital imagery where capturing or displaying a wide range of light and shadow is crucial.
No commits in the last 6 months.
Use this if you need to enhance the dynamic range of a single photograph to achieve more lifelike and detailed visuals.
Not ideal if you already have multiple bracketed exposures of a scene, as traditional HDR merging might offer different control.
Stars
39
Forks
4
Language
Python
License
—
Category
Last pushed
Nov 10, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/compphoto/IntrinsicHDR"
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,...
advimman/HiDT
Official repository for the paper "High-Resolution Daytime Translation Without Domain Labels"...