Unlocking Constraints: Source-Free Occlusion-Aware Seamless Segmentation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Cao, Yihong, Zhang, Jiaming, Zheng, Xu, Shi, Hao, Peng, Kunyu, Liu, Hang, Yang, Kailun, Zhang, Hui
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916866620915712
author Cao, Yihong
Zhang, Jiaming
Zheng, Xu
Shi, Hao
Peng, Kunyu
Liu, Hang
Yang, Kailun
Zhang, Hui
author_facet Cao, Yihong
Zhang, Jiaming
Zheng, Xu
Shi, Hao
Peng, Kunyu
Liu, Hang
Yang, Kailun
Zhang, Hui
contents Panoramic image processing is essential for omni-context perception, yet faces constraints like distortions, perspective occlusions, and limited annotations. Previous unsupervised domain adaptation methods transfer knowledge from labeled pinhole data to unlabeled panoramic images, but they require access to source pinhole data. To address these, we introduce a more practical task, i.e., Source-Free Occlusion-Aware Seamless Segmentation (SFOASS), and propose its first solution, called UNconstrained Learning Omni-Context Knowledge (UNLOCK). Specifically, UNLOCK includes two key modules: Omni Pseudo-Labeling Learning and Amodal-Driven Context Learning. While adapting without relying on source data or target labels, this framework enhances models to achieve segmentation with 360° viewpoint coverage and occlusion-aware reasoning. Furthermore, we benchmark the proposed SFOASS task through both real-to-real and synthetic-to-real adaptation settings. Experimental results show that our source-free method achieves performance comparable to source-dependent methods, yielding state-of-the-art scores of 10.9 in mAAP and 11.6 in mAP, along with an absolute improvement of +4.3 in mAPQ over the source-only method. All data and code will be made publicly available at https://github.com/yihong-97/UNLOCK.
format Preprint
id arxiv_https___arxiv_org_abs_2506_21198
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Unlocking Constraints: Source-Free Occlusion-Aware Seamless Segmentation
Cao, Yihong
Zhang, Jiaming
Zheng, Xu
Shi, Hao
Peng, Kunyu
Liu, Hang
Yang, Kailun
Zhang, Hui
Computer Vision and Pattern Recognition
Robotics
Image and Video Processing
Panoramic image processing is essential for omni-context perception, yet faces constraints like distortions, perspective occlusions, and limited annotations. Previous unsupervised domain adaptation methods transfer knowledge from labeled pinhole data to unlabeled panoramic images, but they require access to source pinhole data. To address these, we introduce a more practical task, i.e., Source-Free Occlusion-Aware Seamless Segmentation (SFOASS), and propose its first solution, called UNconstrained Learning Omni-Context Knowledge (UNLOCK). Specifically, UNLOCK includes two key modules: Omni Pseudo-Labeling Learning and Amodal-Driven Context Learning. While adapting without relying on source data or target labels, this framework enhances models to achieve segmentation with 360° viewpoint coverage and occlusion-aware reasoning. Furthermore, we benchmark the proposed SFOASS task through both real-to-real and synthetic-to-real adaptation settings. Experimental results show that our source-free method achieves performance comparable to source-dependent methods, yielding state-of-the-art scores of 10.9 in mAAP and 11.6 in mAP, along with an absolute improvement of +4.3 in mAPQ over the source-only method. All data and code will be made publicly available at https://github.com/yihong-97/UNLOCK.
title Unlocking Constraints: Source-Free Occlusion-Aware Seamless Segmentation
topic Computer Vision and Pattern Recognition
Robotics
Image and Video Processing
url https://arxiv.org/abs/2506.21198