AIM 2025 Challenge on High FPS Motion Deblurring: Methods and Results

2025-09-08

AI Summary

This work addresses the challenging task of high-frame-rate (high-FPS) single-image non-uniform motion deblurring. Existing methods struggle to model complex, spatiotemporally varying motion patterns. To overcome this limitation, we propose a deep neural network framework that jointly incorporates non-uniform motion priors and spatiotemporal feature aggregation. Furthermore, we introduce MIORe—the first benchmark dataset specifically designed for high-FPS motion deblurring—featuring diverse and highly challenging motion types. MIORe establishes standardized evaluation protocols and has attracted 68 researchers, with nine teams submitting valid solutions. Extensive experiments demonstrate that our method significantly enhances image sharpness and visual quality in dynamic scenes, achieving state-of-the-art performance in high-FPS motion deblurring.

Technology Category

• Computer Vision: Motion & Tracking
• Machine Learning: Multimodal Learning
• Intelligent Robots: Motion and Path Planning

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

This paper presents a comprehensive review of the AIM 2025 High FPS Non-Uniform Motion Deblurring Challenge, highlighting the proposed solutions and final results. The objective of this challenge is to identify effective networks capable of producing clearer and visually compelling images in diverse and challenging conditions, by learning representative visual cues for complex aggregations of motion types. A total of 68 participants registered for the competition, and 9 teams ultimately submitted valid entries. This paper thoroughly evaluates the state-of-the-art advances in high-FPS single image motion deblurring, showcasing the significant progress in the field, while leveraging samples of the novel dataset, MIORe, that introduces challenging examples of movement patterns.

Problem

• Identify networks for clearer images in challenging conditions
• Learn visual cues for complex motion type aggregations
• Evaluate advances in high-FPS single image motion deblurring

Innovation

• High-FPS single image deblurring networks
• Learning representative visual motion cues
• Leveraging novel MIORe dataset samples