|国家预印本平台
首页|Panoramic Out-of-Distribution Segmentation

Panoramic Out-of-Distribution Segmentation

Panoramic Out-of-Distribution Segmentation

来源:Arxiv_logoArxiv
英文摘要

Panoramic imaging enables capturing 360{\deg} images with an ultra-wide Field-of-View (FoV) for dense omnidirectional perception. However, current panoramic semantic segmentation methods fail to identify outliers, and pinhole Out-of-distribution Segmentation (OoS) models perform unsatisfactorily in the panoramic domain due to background clutter and pixel distortions. To address these issues, we introduce a new task, Panoramic Out-of-distribution Segmentation (PanOoS), achieving OoS for panoramas. Furthermore, we propose the first solution, POS, which adapts to the characteristics of panoramic images through text-guided prompt distribution learning. Specifically, POS integrates a disentanglement strategy designed to materialize the cross-domain generalization capability of CLIP. The proposed Prompt-based Restoration Attention (PRA) optimizes semantic decoding by prompt guidance and self-adaptive correction, while Bilevel Prompt Distribution Learning (BPDL) refines the manifold of per-pixel mask embeddings via semantic prototype supervision. Besides, to compensate for the scarcity of PanOoS datasets, we establish two benchmarks: DenseOoS, which features diverse outliers in complex environments, and QuadOoS, captured by a quadruped robot with a panoramic annular lens system. Extensive experiments demonstrate superior performance of POS, with AuPRC improving by 34.25% and FPR95 decreasing by 21.42% on DenseOoS, outperforming state-of-the-art pinhole-OoS methods. Moreover, POS achieves leading closed-set segmentation capabilities. Code and datasets will be available at https://github.com/MengfeiD/PanOoS.

Mengfei Duan、Kailun Yang、Yuheng Zhang、Yihong Cao、Fei Teng、Kai Luo、Jiaming Zhang、Zhiyong Li、Shutao Li

计算技术、计算机技术

Mengfei Duan,Kailun Yang,Yuheng Zhang,Yihong Cao,Fei Teng,Kai Luo,Jiaming Zhang,Zhiyong Li,Shutao Li.Panoramic Out-of-Distribution Segmentation[EB/OL].(2025-05-06)[2025-07-16].https://arxiv.org/abs/2505.03539.点此复制

评论