DOSE3 : Diffusion-based Out-of-distribution detection on SE(3) trajectories

TL;DR

This paper introduces DOSE3, a diffusion-based framework for out-of-distribution detection specifically designed for 3D object pose trajectories in the SE(3) space, addressing a gap in current methods.

Contribution

The work extends diffusion-based OOD detection to SE(3) trajectories, enabling effective detection in robotics and vision applications involving pose sequences.

Findings

DOSE3 outperforms existing OOD detection methods on multiple benchmarks.

The framework effectively handles complex SE(3) trajectory data.

Extends diffusion models to non-Euclidean trajectory spaces.

Abstract

Out-of-Distribution(OOD) detection, a fundamental machine learning task aimed at identifying abnormal samples, traditionally requires model retraining for different inlier distributions. While recent research demonstrates the applicability of diffusion models to OOD detection, existing approaches are limited to Euclidean or latent image spaces. Our work extends OOD detection to trajectories in the Special Euclidean Group in 3D ($\mathbb{SE}(3)$), addressing a critical need in computer vision, robotics, and engineering applications that process object pose sequences in $\mathbb{SE}(3)$. We present $\textbf{D}$iffusion-based $\textbf{O}$ut-of-distribution detection on $\mathbb{SE}(3)$ ($\mathbf{DOSE3}$), a novel OOD framework that extends diffusion to a unified sample space of $\mathbb{SE}(3)$ pose sequences. Through extensive validation on multiple benchmark datasets, we demonstrate $\mathbf{DOSE3}$'s superior performance compared to state-of-the-art OOD detection frameworks.