Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Meng, Yapeng, Yang, Lin, Chen, Yuguo, Chen, Xiangru, Wang, Taoyi, Wang, Lijian, Yang, Zheyu, Lin, Yihan, Zhao, Rong
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2604.10554
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908957470097408
author Meng, Yapeng
Yang, Lin
Chen, Yuguo
Chen, Xiangru
Wang, Taoyi
Wang, Lijian
Yang, Zheyu
Lin, Yihan
Zhao, Rong
author_facet Meng, Yapeng
Yang, Lin
Chen, Yuguo
Chen, Xiangru
Wang, Taoyi
Wang, Lijian
Yang, Zheyu
Lin, Yihan
Zhao, Rong
contents Motion blur arises when rapid scene changes occur during the exposure period, collapsing rich intra-exposure motion into a single RGB frame. Without explicit structural or temporal cues, RGB-only deblurring is highly ill-posed and often fails under extreme motion. Inspired by the human visual system, brain-inspired vision sensors introduce temporally dense information to alleviate this problem. However, event cameras still suffer from event rate saturation under rapid motion, while the event modality entangles edge features and motion cues, which limits their effectiveness. As a recent breakthrough, the complementary vision sensor (CVS), Tianmouc, captures synchronized RGB frames together with high-frame-rate, multi-bit spatial difference (SD, encoding structural edges) and temporal difference (TD, encoding motion cues) data within a single RGB exposure, offering a promising solution for RGB deblurring under extreme dynamic scenes. To fully leverage these complementary modalities, we propose Spatio-Temporal Difference Guided Deblur Net (STGDNet), which adopts a recurrent multi-branch architecture that iteratively encodes and fuses SD and TD sequences to restore structure and color details lost in blurry RGB inputs. Our method outperforms current RGB or event-based approaches in both synthetic CVS dataset and real-world evaluations. Moreover, STGDNet exhibits strong generalization capability across over 100 extreme real-world scenarios. Project page: https://tmcDeblur.github.io/
format Preprint
id arxiv_https___arxiv_org_abs_2604_10554
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Spatio-Temporal Difference Guided Motion Deblurring with the Complementary Vision Sensor
Meng, Yapeng
Yang, Lin
Chen, Yuguo
Chen, Xiangru
Wang, Taoyi
Wang, Lijian
Yang, Zheyu
Lin, Yihan
Zhao, Rong
Computer Vision and Pattern Recognition
Motion blur arises when rapid scene changes occur during the exposure period, collapsing rich intra-exposure motion into a single RGB frame. Without explicit structural or temporal cues, RGB-only deblurring is highly ill-posed and often fails under extreme motion. Inspired by the human visual system, brain-inspired vision sensors introduce temporally dense information to alleviate this problem. However, event cameras still suffer from event rate saturation under rapid motion, while the event modality entangles edge features and motion cues, which limits their effectiveness. As a recent breakthrough, the complementary vision sensor (CVS), Tianmouc, captures synchronized RGB frames together with high-frame-rate, multi-bit spatial difference (SD, encoding structural edges) and temporal difference (TD, encoding motion cues) data within a single RGB exposure, offering a promising solution for RGB deblurring under extreme dynamic scenes. To fully leverage these complementary modalities, we propose Spatio-Temporal Difference Guided Deblur Net (STGDNet), which adopts a recurrent multi-branch architecture that iteratively encodes and fuses SD and TD sequences to restore structure and color details lost in blurry RGB inputs. Our method outperforms current RGB or event-based approaches in both synthetic CVS dataset and real-world evaluations. Moreover, STGDNet exhibits strong generalization capability across over 100 extreme real-world scenarios. Project page: https://tmcDeblur.github.io/
title Spatio-Temporal Difference Guided Motion Deblurring with the Complementary Vision Sensor
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.10554