Visual Programming for Zero-shot Open-Vocabulary 3D Visual Grounding

arXiv:2311.15383v2 Announce Type: replace
Abstract: 3D Visual Grounding (3DVG) aims at localizing 3D object based on textual descriptions. Conventional supervised methods for 3DVG often necessitate extensive annotations and a predefined vocabulary, which can be restrictive. To address this issue, we propose a novel visual programming approach for zero-shot open-vocabulary 3DVG, leveraging the capabilities of large language models (LLMs). Our approach begins with a unique dialog-based method, engaging with LLMs to establish a foundational understanding of zero-shot 3DVG. Building on this, …

3d object abstract annotations arxiv cs.cv issue novel object programming restrictive textual type visual zero-shot