DOSE3 : Diffusion-based Out-of-distribution detection on SE(3) trajectories
It addresses a domain-specific problem for applications like robotics and computer vision that process object pose sequences, representing an incremental extension of diffusion models to a new space.
The paper tackles out-of-distribution detection for trajectories in SE(3) pose sequences, a critical need in robotics and computer vision, by proposing DOSE3, a diffusion-based framework that achieves superior performance compared to state-of-the-art methods on multiple benchmarks.
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.