ViGiL3D: A Linguistically Diverse Dataset for 3D Visual Grounding
This work addresses a bottleneck in 3D visual grounding for embodied AI and scene retrieval by providing a more representative dataset, though it is incremental as it focuses on dataset creation rather than a new method.
The authors tackled the problem of limited linguistic diversity in 3D visual grounding datasets by introducing ViGiL3D, a diagnostic dataset designed to evaluate methods against diverse language patterns, and found that existing methods struggle with out-of-distribution prompts.
3D visual grounding (3DVG) involves localizing entities in a 3D scene referred to by natural language text. Such models are useful for embodied AI and scene retrieval applications, which involve searching for objects or patterns using natural language descriptions. While recent works have focused on LLM-based scaling of 3DVG datasets, these datasets do not capture the full range of potential prompts which could be specified in the English language. To ensure that we are scaling up and testing against a useful and representative set of prompts, we propose a framework for linguistically analyzing 3DVG prompts and introduce Visual Grounding with Diverse Language in 3D (ViGiL3D), a diagnostic dataset for evaluating visual grounding methods against a diverse set of language patterns. We evaluate existing open-vocabulary 3DVG methods to demonstrate that these methods are not yet proficient in understanding and identifying the targets of more challenging, out-of-distribution prompts, toward real-world applications.