Event-Enhanced Blurry Video Super-Resolution

2025-04-11

AAAI Conference on Artificial Intelligence

AI Summary

To address motion modeling deficiencies and high-frequency detail loss in blurry video super-resolution (BVSR)—which cause artifacts and temporal flickering—this paper proposes the first BVSR paradigm integrating event-camera signals. Methodologically, we design a reciprocal feature deblurring module and a hybrid deformable alignment module to enable bidirectional complementary modeling between frames and events; further, we introduce a bidirectional feature enhancement mechanism grounded in event-derived motion priors, jointly leveraging optical flow estimation, deformable convolution, and recursive feature alignment. Our approach achieves state-of-the-art performance on both synthetic and real-world datasets: +2.59 dB PSNR on real scenes and 7.28× faster inference than FMA-Net. The core contribution is the first incorporation of event signals as explicit motion priors into the BVSR framework, significantly improving reconstruction fidelity and robustness for dynamic high-frequency details.

Technology Category

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

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

In this paper, we tackle the task of blurry video super-resolution (BVSR), aiming to generate high-resolution (HR) videos from low-resolution (LR) and blurry inputs. Current BVSR methods often fail to restore sharp details at high resolutions, resulting in noticeable artifacts and jitter due to insufficient motion information for deconvolution and the lack of high-frequency details in LR frames. To address these challenges, we introduce event signals into BVSR and propose a novel event-enhanced network, Ev-DeblurVSR. To effectively fuse information from frames and events for feature deblurring, we introduce a reciprocal feature deblurring module that leverages motion information from intra-frame events to deblur frame features while reciprocally using global scene context from the frames to enhance event features. Furthermore, to enhance temporal consistency, we propose a hybrid deformable alignment module that fully exploits the complementary motion information from inter-frame events and optical flow to improve motion estimation in the deformable alignment process. Extensive evaluations demonstrate that Ev-DeblurVSR establishes a new state-of-the-art performance on both synthetic and real-world datasets. Notably, on real data, our method is 2.59 dB more accurate and 7.28× faster than the recent best BVSR baseline FMA-Net.

Problem

• Enhancing blurry video super-resolution with event signals
• Improving motion estimation using hybrid deformable alignment
• Restoring sharp details in high-resolution videos

Innovation

• Event-enhanced network for blurry video super-resolution
• Reciprocal feature deblurring module using intra-frame events
• Hybrid deformable alignment with inter-frame events and optical flow