时空差分引导的互补视觉传感器运动去模糊
Spatio-Temporal Difference Guided Motion Deblurring with the Complementary Vision Sensor
把 CVS 传感器输出的高帧率多比特空间差分（SD，编码结构边缘）与时序差分（TD，编码运动线索）作为额外模态，用循环多分支网络迭代编码融合来引导 RGB 去模糊，为极端运动下的复原提供了「事件相机之外」的新传感模态与融合范式。
原文依据 captures synchronized RGB frames together with high-frame-rate, multi-bit spatial difference (SD, encoding structural edges) and temporal difference (TD, encoding motion cues)
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论当曝光期间发生快速场景变化时，丰富的曝光内运动被压缩进单帧 RGB 图像，从而产生运动模糊。在缺乏显式结构或时序线索的情况下，仅依赖 RGB 的去模糊问题高度病态，在极端运动下往往失效。受人类视觉系统启发，类脑视觉传感器引入时序稠密信息以缓解该问题。然而，事件相机在快速运动下仍会出现事件率饱和，且事件模态将边缘特征与运动线索纠缠在一起，限制了其有效性。作为近期突破，互补视觉传感器（CVS）Tianmouc 在单次 RGB 曝光内同步捕获 RGB 帧与高帧率、多比特的空间差分（SD，编码结构边缘）和时序差分（TD，编码运动线索）数据，为极端动态场景下的 RGB 去模糊提供了有前景的解决方案。为充分利用这些互补模态，本文提出时空差分引导去模糊网络（STGDNet），采用循环多分支架构，迭代地编码并融合 SD 与 TD 序列，以恢复模糊 RGB 输入中丢失的结构与颜色细节。本方法在合成 CVS 数据集与真实世界评测中均优于现有基于 RGB 或事件的方法。此外，STGDNet 在 100 多个极端真实场景中展现出强泛化能力。项目主页：https://tmcDeblur.github.io/
英文原文摘要 1502 字符
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/