LLM-Grounder: Open-Vocabulary 3D Visual Grounding with Large Language Model as an Agent
Abstract
3D visual grounding is a critical skill for household robots, enabling them to navigate, manipulate objects, and answer questions based on their environment. While existing approaches often rely on extensive labeled data or exhibit limitations in handling complex language queries, we propose LLM-Grounder, a novel zero-shot, open-vocabulary, Large Language Model (LLM)-based 3D visual grounding pipeline. LLM-Grounder utilizes an LLM to decompose complex natural language queries into semantic constituents and employs a visual grounding tool, such as OpenScene or LERF, to identify objects in a 3D scene. The LLM then evaluates the spatial and commonsense relations among the proposed objects to make a final grounding decision. Our method does not require any labeled training data and can generalize to novel 3D scenes and arbitrary text queries. We evaluate LLM-Grounder on the ScanRefer benchmark and demonstrate state-of-the-art zero-shot grounding accuracy. Our findings indicate that LLMs significantly improve the grounding capability, especially for complex language queries, making LLM-Grounder an effective approach for 3D vision-language tasks in robotics. Videos and interactive demos can be found on the project website https://chat-with-nerf.github.io/ .
Community
Please see our latest video demo here: https://youtu.be/eO-Vaf-1R1s. Thanks!
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Multi3DRefer: Grounding Text Description to Multiple 3D Objects (2023)
- ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning (2023)
- Context-Aware Entity Grounding with Open-Vocabulary 3D Scene Graphs (2023)
- Three Ways to Improve Verbo-visual Fusion for Dense 3D Visual Grounding (2023)
- Dense Object Grounding in 3D Scenes (2023)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper