VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding
It addresses data scarcity in robotics by enabling zero-shot 3D grounding without 3D data, though it is incremental as it builds on existing zero-shot approaches.
The paper tackles 3D visual grounding for robots by proposing VLM-Grounder, a zero-shot framework using vision-language models on 2D images, which achieves 51.6% Acc@0.25 on ScanRefer and 48.0% Acc on Nr3D, outperforming prior methods.
3D visual grounding is crucial for robots, requiring integration of natural language and 3D scene understanding. Traditional methods depending on supervised learning with 3D point clouds are limited by scarce datasets. Recently zero-shot methods leveraging LLMs have been proposed to address the data issue. While effective, these methods only use object-centric information, limiting their ability to handle complex queries. In this work, we present VLM-Grounder, a novel framework using vision-language models (VLMs) for zero-shot 3D visual grounding based solely on 2D images. VLM-Grounder dynamically stitches image sequences, employs a grounding and feedback scheme to find the target object, and uses a multi-view ensemble projection to accurately estimate 3D bounding boxes. Experiments on ScanRefer and Nr3D datasets show VLM-Grounder outperforms previous zero-shot methods, achieving 51.6% Acc@0.25 on ScanRefer and 48.0% Acc on Nr3D, without relying on 3D geometry or object priors. Codes are available at https://github.com/OpenRobotLab/VLM-Grounder .