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

2026-04-12

AI Summary

This work addresses the challenge of restoring RGB images degraded by motion blur in high-speed scenarios, where conventional methods struggle due to the absence of structural and temporal cues. To overcome this limitation, the authors propose STGDNet, a novel approach that leverages a complementary vision sensor, Tianmouc, to simultaneously capture RGB frames along with high-frame-rate, multi-bit spatial difference (SD) and temporal difference (TD) data. A recurrent multi-branch network is designed to explicitly incorporate structural and motion priors through an SD/TD-guided iterative fusion mechanism. Evaluated on both synthetic and over one hundred real-world extreme dynamic scenes, STGDNet substantially outperforms existing RGB- or event camera–based deblurring methods, achieving superior detail recovery and strong generalization capability.

Technology Category

• Computer Vision: Motion & Tracking
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multimodal Learning

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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/

Problem

• motion deblurring
• extreme motion
• RGB deblurring
• spatio-temporal cues
• ill-posed problem

Innovation

• Complementary Vision Sensor
• Spatio-Temporal Difference
• Motion Deblurring
• STGDNet
• Multi-branch Recurrent Fusion