zlccccc/3DVL_Codebase

[CVPR2022 Oral] 3DJCG: A Unified Framework for Joint Dense Captioning and Visual Grounding on 3D Point Clouds

33
/ 100
Emerging

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.

3D-scene-understanding robotics-perception augmented-reality computer-vision natural-language-interaction
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

57

Forks

4

Language

Python

License

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.