Jumpat/SegmentAnythingin3D
Segment Anything in 3D with NeRFs (NeurIPS 2023 & IJCV 2025)
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.
Stars
1,014
Forks
65
Language
Python
License
Apache-2.0
Category
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.
Related tools
weiyithu/NerfingMVS
[ICCV 2021 Oral] NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo
POSTECH-CVLab/SCNeRF
[ICCV21] Self-Calibrating Neural Radiance Fields
half-potato/nmf
Our method takes as input a collection of images (100 in our experiments) with known cameras,...
synthesiaresearch/humanrf
Official code for "HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion"
HankYe/PAGCP
[T-PAMI'23] PAGCP for the compression of YOLOv5