PanoVOS: Bridging Non-panoramic and Panoramic Views with Transformer for Video Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yan, Shilin, Xu, Xiaohao, Zhang, Renrui, Hong, Lingyi, Chen, Wenchao, Zhang, Wenqiang, Zhang, Wei
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916338405998592
author Yan, Shilin
Xu, Xiaohao
Zhang, Renrui
Hong, Lingyi
Chen, Wenchao
Zhang, Wenqiang
Zhang, Wei
author_facet Yan, Shilin
Xu, Xiaohao
Zhang, Renrui
Hong, Lingyi
Chen, Wenchao
Zhang, Wenqiang
Zhang, Wei
contents Panoramic videos contain richer spatial information and have attracted tremendous amounts of attention due to their exceptional experience in some fields such as autonomous driving and virtual reality. However, existing datasets for video segmentation only focus on conventional planar images. To address the challenge, in this paper, we present a panoramic video dataset, PanoVOS. The dataset provides 150 videos with high video resolutions and diverse motions. To quantify the domain gap between 2D planar videos and panoramic videos, we evaluate 15 off-the-shelf video object segmentation (VOS) models on PanoVOS. Through error analysis, we found that all of them fail to tackle pixel-level content discontinues of panoramic videos. Thus, we present a Panoramic Space Consistency Transformer (PSCFormer), which can effectively utilize the semantic boundary information of the previous frame for pixel-level matching with the current frame. Extensive experiments demonstrate that compared with the previous SOTA models, our PSCFormer network exhibits a great advantage in terms of segmentation results under the panoramic setting. Our dataset poses new challenges in panoramic VOS and we hope that our PanoVOS can advance the development of panoramic segmentation/tracking.
format Preprint
id arxiv_https___arxiv_org_abs_2309_12303
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle PanoVOS: Bridging Non-panoramic and Panoramic Views with Transformer for Video Segmentation
Yan, Shilin
Xu, Xiaohao
Zhang, Renrui
Hong, Lingyi
Chen, Wenchao
Zhang, Wenqiang
Zhang, Wei
Computer Vision and Pattern Recognition
Panoramic videos contain richer spatial information and have attracted tremendous amounts of attention due to their exceptional experience in some fields such as autonomous driving and virtual reality. However, existing datasets for video segmentation only focus on conventional planar images. To address the challenge, in this paper, we present a panoramic video dataset, PanoVOS. The dataset provides 150 videos with high video resolutions and diverse motions. To quantify the domain gap between 2D planar videos and panoramic videos, we evaluate 15 off-the-shelf video object segmentation (VOS) models on PanoVOS. Through error analysis, we found that all of them fail to tackle pixel-level content discontinues of panoramic videos. Thus, we present a Panoramic Space Consistency Transformer (PSCFormer), which can effectively utilize the semantic boundary information of the previous frame for pixel-level matching with the current frame. Extensive experiments demonstrate that compared with the previous SOTA models, our PSCFormer network exhibits a great advantage in terms of segmentation results under the panoramic setting. Our dataset poses new challenges in panoramic VOS and we hope that our PanoVOS can advance the development of panoramic segmentation/tracking.
title PanoVOS: Bridging Non-panoramic and Panoramic Views with Transformer for Video Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2309.12303