Bridge Frame and Event: Common Spatiotemporal Fusion for High-Dynamic Optical Flow

Hanyu Zhou, Haonan Wang, Shihan Peng, Haoyue Liu, Yuxing Duan, Yi Chang, Luxin Yan

Keywords: high-dynamic scene, optical flow, event camera, multimodal fusion

TL;DR: We propose a novel common spatiotemporal fusion between frame and event modalities for high-dynamic scene optical flow.

Abstract: High-dynamic scene optical flow is a challenging task, which suffers large displacement. Limited by frame imaging, large displacement causes potential spatial blurry textures due to long exposure and temporal discontinuous motion due to low frame rate, thus deteriorating the spatiotemporal feature of optical flow. Typically, existing methods mainly introduce event camera with high temporal resolution to directly fuse the spatiotemporal features between the two modalities. However, this direct fusion is ineffective, since there exists a large gap due to the heterogeneous data representation between frame and event modalities. To address this issue, we explore a common-latent space as an intermediate bridge to mitigate the modality gap. In this work, we propose a novel common spatiotemporal fusion between frame and event modalities for high-dynamic scene optical flow, including visual boundary localization and motion correlation fusion. Specifically, in visual boundary localization, we figure out that frame and event can be derived into the spatiotemporal gradient maps with the same data representation, where the similarity distribution between the two modalities is consistent with the extracted boundary distribution. This motivates us to design the common spatiotemporal gradient to constrain the localization of the reference boundary as a template. In motion correlation fusion, we discover that the frame-based motion possesses spatially dense but temporally discontinuous correlation, while the event-based motion has spatially sparse but temporally continuous correlation. This inspires us to take the reference boundary template to guide the fusion of the complementary motion knowledge between the two modalities. Moreover, common spatiotemporal fusion can not only relieve the cross-modal feature discrepancy, but also make the fusion process interpretable to achieve dense and continuous optical flow. Extensive experiments have been performed to verify the superiority of the proposed method.

Primary Area: applications to computer vision, audio, language, and other modalities

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 114