Thanks to visit codestin.com
Credit goes to github.com

Skip to content
/ ScanReason Public
forked from ZCMax/ScanReason

[ECCV 2024] Empowering 3D Visual Grounding with Reasoning Capabilities

0 stars 3 forks Branches Tags Activity
Star

vpeiyun97/ScanReason

BranchesTags
 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
assets
assets
 
 
README.md
README.md
 
 

Repository files navigation


Empowering 3D Visual Grounding with Reasoning Capabilities

ECCV 2024
Chenming Zhu  Tai Wang  Wenwei Zhang  Kai Chen  Xihui Liu* 
The University of Hong Kong Shanghai AI Laboratory

arXiv

🏠 Background

Dialogue_Teaser
For an embodied agent, they not only need to be able to understand the 3D environment and complex human instructions, but also localize the target objects for interaction and navigation. Although GPT-4 (GPT-4V) have strong text (multi-modal) reasoning abilities, they lack the ability to directly perceive the 3D scene, understand the 3D spatial relationships and output corresponding target object locations. In this paper, we propose a new task called 3D reasoning grounding and introduce a new benchmark **ScanReason** which provides over 10K question-answer-location pairs from five reasoning types that require the synerization of reasoning and grounding. We further design our approach, ReGround3D, composed of the visual-centric reasoning module empowered by Multi-modal Large Language Model (MLLM) and the 3D grounding module to obtain accurate object locations by looking back to the enhanced geometry and fine-grained details from the 3D scenes. A chain-of-grounding mechanism is proposed to further boost the performance with interleaved reasoning and grounding steps during inference.

📦 Benchmark and Model

Benchmark Overview

ScanReason is the first comprehensive and hierarchical 3D reasoning grounding benchmark. We define 5 types of questions depending on which type of reasoning is required: Spatial reasoning and function reasoning require fundamental understanding of the 3D physical world, focusing on objects themselves and inter-object spatial relationships in a 3D scene respectively, and logistic reasoning, emotional reasoning, and safety reasoning are high-level reasoning skills built upon the two fundamental reasoning abilities to address user-centric real-world applications.

Model Overview

📝 TODO List

  • First Release.
  • Release ScanReason datasets and benchmark.
  • Release ReGround3D code.

📄 License

Creative Commons License
This work is under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

👏 Acknowledgements

This repo benefits from LISA, EmbodiedScan, 3D-LLM, LLaVA.

About

[ECCV 2024] Empowering 3D Visual Grounding with Reasoning Capabilities

Resources

Readme
Activity

Stars

0 stars

Watchers

0 watching

Forks

0 forks
Report repository

Releases

No releases published

Packages

No packages published