fraunhoferhhi/neural-deferred-shading
Multi-View Mesh Reconstruction with Neural Deferred Shading (CVPR 2022)
This project helps 3D artists, game developers, or researchers reconstruct detailed 3D models from multiple photographs. You input a set of images taken from different angles around an object, along with camera positioning and an approximate bounding box. The output is a high-fidelity 3D mesh model of the object, which can then be viewed or further processed.
266 stars. No commits in the last 6 months.
Use this if you need to create accurate 3D mesh representations of real-world objects from a collection of images, especially for applications requiring precise geometry.
Not ideal if you're looking for a simple, automated 3D scanning solution without needing to provide camera parameters, or if your primary goal is real-time capture rather than detailed offline reconstruction.
Stars
266
Forks
21
Language
Python
License
—
Category
Last pushed
May 26, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/fraunhoferhhi/neural-deferred-shading"
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)