compphoto/Intrinsic
Repo for the papers "Intrinsic Image Decomposition via Ordinal Shading" (TOG 2023) and "Colorful Diffuse Intrinsic Image Decomposition in the Wild" (TOG 2024)
This project helps photographers and digital artists separate the true color of an object from the effects of lighting and shadows in their images. You provide an ordinary photograph, and it outputs layers showing the object's inherent color (albedo), how it's lit, and any shiny reflections, enabling detailed, illumination-aware editing. This is for anyone who needs to manipulate image appearance independent of how it was lit.
338 stars. No commits in the last 6 months.
Use this if you need to precisely adjust colors, remove glare, or alter lighting in an existing photograph without affecting the underlying object's true appearance.
Not ideal if you are looking for a simple, one-click photo filter or if you are working with non-photographic, abstract imagery.
Stars
338
Forks
22
Language
Python
License
—
Category
Last pushed
Apr 09, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/compphoto/Intrinsic"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
rundiwu/DeepCAD
code for our ICCV 2021 paper "DeepCAD: A Deep Generative Network for Computer-Aided Design Models"
XingangPan/GAN2Shape
Code for GAN2Shape (ICLR2021 oral)
ayaanzhaque/instruct-nerf2nerf
Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions (ICCV 2023)
mworchel/differentiable-shadow-mapping
Differentiable Shadow Mapping for Efficient Inverse Graphics (CVPR 2023)
cgtuebingen/SIGNeRF
SIGNeRF: Scene Integrated Generation for Neural Radiance Fields