Instance-Level Moving Object Segmentation from a Single Image with Events

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wan, Zhexiong, Fan, Bin, Hui, Le, Dai, Yuchao, Lee, Gim Hee
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910834770313216
author Wan, Zhexiong
Fan, Bin
Hui, Le
Dai, Yuchao
Lee, Gim Hee
author_facet Wan, Zhexiong
Fan, Bin
Hui, Le
Dai, Yuchao
Lee, Gim Hee
contents Moving object segmentation plays a crucial role in understanding dynamic scenes involving multiple moving objects, while the difficulties lie in taking into account both spatial texture structures and temporal motion cues. Existing methods based on video frames encounter difficulties in distinguishing whether pixel displacements of an object are caused by camera motion or object motion due to the complexities of accurate image-based motion modeling. Recent advances exploit the motion sensitivity of novel event cameras to counter conventional images' inadequate motion modeling capabilities, but instead lead to challenges in segmenting pixel-level object masks due to the lack of dense texture structures in events. To address these two limitations imposed by unimodal settings, we propose the first instance-level moving object segmentation framework that integrates complementary texture and motion cues. Our model incorporates implicit cross-modal masked attention augmentation, explicit contrastive feature learning, and flow-guided motion enhancement to exploit dense texture information from a single image and rich motion information from events, respectively. By leveraging the augmented texture and motion features, we separate mask segmentation from motion classification to handle varying numbers of independently moving objects. Through extensive evaluations on multiple datasets, as well as ablation experiments with different input settings and real-time efficiency analysis of the proposed framework, we believe that our first attempt to incorporate image and event data for practical deployment can provide new insights for future work in event-based motion related works. The source code with model training and pre-trained weights is released at https://npucvr.github.io/EvInsMOS
format Preprint
id arxiv_https___arxiv_org_abs_2502_12975
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Instance-Level Moving Object Segmentation from a Single Image with Events
Wan, Zhexiong
Fan, Bin
Hui, Le
Dai, Yuchao
Lee, Gim Hee
Computer Vision and Pattern Recognition
Moving object segmentation plays a crucial role in understanding dynamic scenes involving multiple moving objects, while the difficulties lie in taking into account both spatial texture structures and temporal motion cues. Existing methods based on video frames encounter difficulties in distinguishing whether pixel displacements of an object are caused by camera motion or object motion due to the complexities of accurate image-based motion modeling. Recent advances exploit the motion sensitivity of novel event cameras to counter conventional images' inadequate motion modeling capabilities, but instead lead to challenges in segmenting pixel-level object masks due to the lack of dense texture structures in events. To address these two limitations imposed by unimodal settings, we propose the first instance-level moving object segmentation framework that integrates complementary texture and motion cues. Our model incorporates implicit cross-modal masked attention augmentation, explicit contrastive feature learning, and flow-guided motion enhancement to exploit dense texture information from a single image and rich motion information from events, respectively. By leveraging the augmented texture and motion features, we separate mask segmentation from motion classification to handle varying numbers of independently moving objects. Through extensive evaluations on multiple datasets, as well as ablation experiments with different input settings and real-time efficiency analysis of the proposed framework, we believe that our first attempt to incorporate image and event data for practical deployment can provide new insights for future work in event-based motion related works. The source code with model training and pre-trained weights is released at https://npucvr.github.io/EvInsMOS
title Instance-Level Moving Object Segmentation from a Single Image with Events
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2502.12975