Jumpat/SegmentAnythingin3D

Segment Anything in 3D with NeRFs (NeurIPS 2023 & IJCV 2025)

44
/ 100
Emerging

This tool helps researchers and 3D artists quickly isolate specific objects from complex 3D scenes. By providing a 3D scene model (NeRF) and a simple prompt (like a click or text description) from a single viewpoint, it automatically generates a complete 3D model of the desired object. This is ideal for those who need to extract individual elements from a full 3D capture.

1,014 stars. No commits in the last 6 months.

Use this if you need to precisely segment and extract individual objects from a neural radiance field (NeRF) or 3D Gaussian Splatting model with minimal manual effort.

Not ideal if you don't work with NeRFs or 3D Gaussian Splatting, or if you need to create entirely new 3D models from scratch.

3D-reconstruction computer-graphics scene-understanding virtual-reality asset-extraction
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

1,014

Forks

65

Language

Python

License

Apache-2.0

Last pushed

May 19, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Jumpat/SegmentAnythingin3D"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.