NVlabs/nvdiffrec
Official code for the CVPR 2022 (oral) paper "Extracting Triangular 3D Models, Materials, and Lighting From Images".
This tool helps 3D artists, game developers, or anyone working with visual assets create accurate 3D models. It takes multiple 2D images of an object, along with its associated lighting, and reconstructs a detailed 3D triangular mesh model with its material properties. This is ideal for generating digital assets from real-world objects or improving existing 3D models.
2,270 stars. No commits in the last 6 months.
Use this if you need to generate high-fidelity 3D models, including their surface textures and how they react to light, directly from a set of photographs.
Not ideal if you're looking for a simple 2D image editing tool or if you don't have multiple images of your target object captured from different angles.
Stars
2,270
Forks
242
Language
Python
License
—
Category
Last pushed
May 02, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/NVlabs/nvdiffrec"
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
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)
fraunhoferhhi/neural-deferred-shading
Multi-View Mesh Reconstruction with Neural Deferred Shading (CVPR 2022)