Spatio-Temporal Difference Guided Motion Deblurring with the Complementary Vision Sensor
For computer vision applications requiring robust deblurring under rapid motion, this work introduces a new sensor modality and a tailored architecture that significantly improves performance over prior state-of-the-art.
This paper tackles motion deblurring under extreme dynamic scenes by leveraging a novel complementary vision sensor (CVS) that provides synchronized RGB, spatial difference (SD), and temporal difference (TD) data. The proposed STGDNet outperforms existing RGB and event-based methods on synthetic and real-world benchmarks, demonstrating strong generalization across over 100 extreme scenarios.
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/