Totoro97/NeuS

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1775 stars · 223 forks observed · 2026-10-01

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Official PyTorch implementation of NeuS, a neural implicit surface reconstruction method that learns SDF-based surfaces via volume rendering from multi-view 2D images. It supports training with or without masks and exports reconstructed meshes as PLY files.

Use cases

• reconstruct 3d surfaces from multi-view images
• neural implicit surface reconstruction from photos
• extract meshes from 2d image sets
• 3d reconstruction without depth sensors
• view interpolation from multi-view captures
• reproduce NeuS paper results

When to choose

• you need high-fidelity object or scene reconstruction from calibrated multi-view images
• you want a research baseline for neural implicit surface methods
• you have masks or can run mask-free training on your captures

When to avoid

• you need real-time reconstruction
• you lack GPU resources or calibrated camera parameters
• you want a production-ready photogrammetry pipeline rather than research code

Facets

library · maturity stable

machine-learning deep-learning computer-vision image-processing graphics computer-vision deep-learning graphics machine-learning python neural-implicit-surfaces neural-rendering 3d-reconstruction volume-rendering sdf multi-view-stereo research-code linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Totoro97/NeuS")