Spatio-Temporal Difference Guided Motion Deblurring with the Complementary Vision Sensor

TL;DR

This paper introduces STGDNet, a novel neural network that leverages the complementary vision sensor's structural and motion data to significantly improve motion deblurring in extreme dynamic scenes.

Contribution

The paper proposes a recurrent multi-branch architecture that effectively fuses structural and motion cues from the CVS to enhance RGB deblurring, outperforming existing methods.

Findings

Outperforms current RGB and event-based deblurring approaches.

Demonstrates strong generalization across over 100 real-world scenarios.

Effectively restores details in extreme motion scenes.

Abstract

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/