SODA: Out-of-Distribution Detection in Domain-Shifted Point Clouds via Neighborhood Propagation

TL;DR

This paper introduces SODA, a neighborhood propagation method for out-of-distribution detection in point clouds, addressing domain shift issues between synthetic training data and real-world scans, achieving state-of-the-art results.

Contribution

SODA is a novel inference-based approach that enhances OOD detection in point clouds without additional training, effectively handling synthetic-to-real domain shifts.

Findings

SODA outperforms existing methods across multiple datasets.

Domain shift significantly impacts point cloud OOD detection performance.

Neighborhood propagation improves alignment in 3D VLM latent space.

Abstract

As point cloud data increases in prevalence in a variety of applications, the ability to detect out-of-distribution (OOD) point cloud objects becomes critical for ensuring model safety and reliability. However, this problem remains under-explored in existing research. Inspired by success in the image domain, we propose to exploit advances in 3D vision-language models (3D VLMs) for OOD detection in point cloud objects. However, a major challenge is that point cloud datasets used to pre-train 3D VLMs are drastically smaller in size and object diversity than their image-based counterparts. Critically, they often contain exclusively computer-designed synthetic objects. This leads to a substantial domain shift when the model is transferred to practical tasks involving real objects scanned from the physical environment. In this paper, our empirical experiments show that synthetic-to-real domain shift significantly degrades the alignment of point cloud with their associated text embeddings in the 3D VLM latent space, hindering downstream performance. To address this, we propose a novel methodology called SODA which improves the detection of OOD point clouds through a neighborhood-based score propagation scheme. SODA is inference-based, requires no additional model training, and achieves state-of-the-art performance over existing approaches across datasets and problem settings.