pengsongyou/openscene
[CVPR'23] OpenScene: 3D Scene Understanding with Open Vocabularies
This project helps anyone working with 3D environment scans to quickly identify and highlight specific objects, materials, properties, or even abstract concepts within those scans. You provide a 3D scan or depth data, type in a descriptive phrase like "festive" or "made of metal," and the system highlights the corresponding regions. This is ideal for professionals in fields like architecture, interior design, robotics, or virtual reality development who need to understand and interact with 3D scene data.
800 stars. No commits in the last 6 months.
Use this if you need to perform real-time, interactive searches within complex 3D scans using natural language descriptions, even for rare objects or abstract ideas.
Not ideal if your primary goal is standard object detection with a fixed, predefined list of categories or if you don't work with 3D scene data.
Stars
800
Forks
65
Language
Python
License
Apache-2.0
Category
Last pushed
Oct 27, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/pengsongyou/openscene"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
col14m/cadrille
[ICLR2026] cadrille: Multi-modal CAD Reconstruction with Online Reinforcement Learning
filaPro/cad-recode
[ICCV2025] CAD-Recode: Reverse Engineering CAD Code from Point Clouds
worldbench/3EED
[NeurIPS 2025 DB Track] 3EED: Ground Everything Everywhere in 3D
cambrian-mllm/cambrian-s
Cambrian-S: Towards Spatial Supersensing in Video
Gorilla-Lab-SCUT/PaDT
[ICLR 2026] Official implementation of "Patch-as-Decodable-Token: Towards Unified Multi-Modal...