facebookresearch/DeepSDF

Health v2 · maintenance only

Flags: no_releases archived

Adoption not part of the score

1563 stars · 281 forks observed · 2026-08-28

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

DeepSDF is Facebook Research's official implementation of the CVPR 2019 paper on learning continuous signed distance functions for 3D shape representation. It provides Python scripts for preprocessing meshes, training latent-code-based SDF models, reconstructing shapes, and evaluating with Chamfer and Earth Mover's Distance metrics.

Use cases

• learn continuous signed distance functions for 3D shapes
• reconstruct 3D meshes from point clouds
• train shape representation models on mesh datasets
• preprocess mesh datasets into SDF samples
• evaluate 3D reconstruction quality with Chamfer distance
• research neural implicit shape representations

When to choose

• you need the reference implementation of DeepSDF for research
• you want to train neural implicit SDF models on mesh collections
• you need reproducible 3D shape reconstruction baselines

When to avoid

• you need a production-ready 3D processing pipeline
• you want actively maintained code with recent updates
• you need a general-purpose 3D mesh editing tool

Facets

library · maturity maintenance

machine-learning deep-learning graphics simulation machine-learning computer-vision graphics deep-learning python signed-distance-functions shape-representation 3d-reconstruction research-code cvpr-2019 linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="facebookresearch/DeepSDF")