Morpheus3000/PIE-Net
Official model and network release for my CVPR2022 paper.
This project helps you to automatically separate the inherent color and texture of an object from the effects of lighting and shadows in a single photograph. You provide an image, and it outputs two new images: one showing the true colors and textures (albedo), and another showing just the lighting and shadows. This is useful for computer vision researchers and anyone working with image analysis where lighting variations interfere with object recognition or material understanding.
No commits in the last 6 months.
Use this if you need to reliably identify objects or analyze surface properties in images, even when they are taken under different or challenging lighting conditions.
Not ideal if you are looking for a tool to perform general image editing or require advanced artistic control over lighting and shadow manipulation.
Stars
51
Forks
11
Language
Python
License
—
Category
Last pushed
Oct 24, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Morpheus3000/PIE-Net"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
anchen1011/toflow
TOFlow: Video Enhancement with Task-Oriented Flow
NVlabs/nvdiffrec
Official code for the CVPR 2022 (oral) paper "Extracting Triangular 3D Models, Materials, and...
RuojinCai/doppelgangers
Doppelgangers: Learning to Disambiguate Images of Similar Structures
cvg/GlueStick
Joint Deep Matcher for Points and Lines 🖼️💥🖼️ (ICCV 2023)
microsoft/SpareNet
Style-based Point Generator with Adversarial Rendering for Point Cloud Completion (CVPR 2021)