Saved in:
Bibliographic Details
Main Authors: Liu, Daikun, Cheng, Lei, Wang, Teng, Sun, changyin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.03512
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912439329619968
author Liu, Daikun
Cheng, Lei
Wang, Teng
Sun, changyin
author_facet Liu, Daikun
Cheng, Lei
Wang, Teng
Sun, changyin
contents Recent learning-based methods for event-based optical flow estimation utilize cost volumes for pixel matching but suffer from redundant computations and limited scalability to higher resolutions for flow refinement. In this work, we take advantage of the complementarity between temporally dense feature differences of adjacent event frames and cost volume and present a lightweight event-based optical flow network (EDCFlow) to achieve high-quality flow estimation at a higher resolution. Specifically, an attention-based multi-scale temporal feature difference layer is developed to capture diverse motion patterns at high resolution in a computation-efficient manner. An adaptive fusion of high-resolution difference motion features and low-resolution correlation motion features is performed to enhance motion representation and model generalization. Notably, EDCFlow can serve as a plug-and-play refinement module for RAFT-like event-based methods to enhance flow details. Extensive experiments demonstrate that EDCFlow achieves better performance with lower complexity compared to existing methods, offering superior generalization.
format Preprint
id arxiv_https___arxiv_org_abs_2506_03512
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EDCFlow: Exploring Temporally Dense Difference Maps for Event-based Optical Flow Estimation
Liu, Daikun
Cheng, Lei
Wang, Teng
Sun, changyin
Computer Vision and Pattern Recognition
Recent learning-based methods for event-based optical flow estimation utilize cost volumes for pixel matching but suffer from redundant computations and limited scalability to higher resolutions for flow refinement. In this work, we take advantage of the complementarity between temporally dense feature differences of adjacent event frames and cost volume and present a lightweight event-based optical flow network (EDCFlow) to achieve high-quality flow estimation at a higher resolution. Specifically, an attention-based multi-scale temporal feature difference layer is developed to capture diverse motion patterns at high resolution in a computation-efficient manner. An adaptive fusion of high-resolution difference motion features and low-resolution correlation motion features is performed to enhance motion representation and model generalization. Notably, EDCFlow can serve as a plug-and-play refinement module for RAFT-like event-based methods to enhance flow details. Extensive experiments demonstrate that EDCFlow achieves better performance with lower complexity compared to existing methods, offering superior generalization.
title EDCFlow: Exploring Temporally Dense Difference Maps for Event-based Optical Flow Estimation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.03512