zlccccc/3DVL_Codebase
[CVPR2022 Oral] 3DJCG: A Unified Framework for Joint Dense Captioning and Visual Grounding on 3D Point Clouds
This project helps developers working with 3D data understand and describe objects within 3D point clouds. You input a 3D point cloud and natural language descriptions or questions about specific objects. The output is either the precise 3D location of the described object, detailed text captions for multiple objects, or answers to questions about objects in the scene. This is for researchers and developers in computer vision, robotics, and augmented reality who are building advanced 3D scene understanding applications.
No commits in the last 6 months.
Use this if you are a researcher or developer focused on building systems that can interpret and interact with 3D environments based on language instructions.
Not ideal if you need a plug-and-play solution for general 3D object detection or scene reconstruction without integrating natural language processing.
Stars
57
Forks
4
Language
Python
License
—
Category
Last pushed
Jan 29, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/zlccccc/3DVL_Codebase"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
isl-org/Open3D
Open3D: A Modern Library for 3D Data Processing
cvg/Hierarchical-Localization
Visual localization made easy with hloc
gmberton/CosPlace
Official code for CVPR 2022 paper "Rethinking Visual Geo-localization for Large-Scale Applications"
Vincentqyw/image-matching-webui
🤗 image matching webui
cvg/glue-factory
Training library for local feature detection and matching