Exploiting Vision Language Model for Training-Free 3D Point Cloud OOD Detection via Graph Score Propagation
This addresses the problem of safe and robust perception in 3D environments for applications like autonomous systems, though it is incremental as it extends existing VLM-based approaches to 3D data.
The paper tackles the challenge of out-of-distribution (OOD) detection in 3D point cloud data by introducing a training-free framework that leverages Vision-Language Models (VLMs) with a Graph Score Propagation (GSP) method, resulting in consistent outperformance of state-of-the-art methods across synthetic and real-world datasets.
Out-of-distribution (OOD) detection in 3D point cloud data remains a challenge, particularly in applications where safe and robust perception is critical. While existing OOD detection methods have shown progress for 2D image data, extending these to 3D environments involves unique obstacles. This paper introduces a training-free framework that leverages Vision-Language Models (VLMs) for effective OOD detection in 3D point clouds. By constructing a graph based on class prototypes and testing data, we exploit the data manifold structure to enhancing the effectiveness of VLMs for 3D OOD detection. We propose a novel Graph Score Propagation (GSP) method that incorporates prompt clustering and self-training negative prompting to improve OOD scoring with VLM. Our method is also adaptable to few-shot scenarios, providing options for practical applications. We demonstrate that GSP consistently outperforms state-of-the-art methods across synthetic and real-world datasets 3D point cloud OOD detection.