perceivelab/surfacenet
The official PyTorch implementation for paper "SurfaceNet: Adversarial SVBRDF Estimation from a Single Image"
This project helps 3D artists, game developers, and product designers reconstruct detailed material properties from a single photograph. You provide one image of an object, and it generates separate maps describing its color, shininess, roughness, and transparency. This allows for realistic rendering of objects in virtual environments or for material analysis.
No commits in the last 6 months.
Use this if you need to accurately capture and separate the surface characteristics (like how light reflects and scatters) of a real-world object from a single photo for use in 3D modeling or rendering.
Not ideal if you need to reconstruct 3D geometry or if you have multiple images and advanced scanning equipment for extremely precise material capture.
Stars
45
Forks
5
Language
Python
License
MIT
Category
Last pushed
Nov 03, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/perceivelab/surfacenet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
NVlabs/instant-ngp
Instant neural graphics primitives: lightning fast NeRF and more
nerfstudio-project/nerfstudio
A collaboration friendly studio for NeRFs
google/nerfies
This is the code for Deformable Neural Radiance Fields, a.k.a. Nerfies.
SuLvXiangXin/zipnerf-pytorch
Unofficial implementation of ZipNeRF
google/hypernerf
Code for "HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural...