发表机构
Korea Advanced Institute of Science and Technology（韩国科学技术院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出事件引导模糊合成框架EvBS，通过解耦运动与内容生成多样训练对，提升预训练去模糊模型的域自适应性能，经多基准实验验证其可增强模型在未见测试集上的鲁棒性。
AI 中文摘要
运动去模糊通过深度学习已取得显著进展，但预训练的去模糊模型常因训练与测试分布间的域偏移，在真实场景中出现性能下降。为解决该问题，本文提出EvBS，一种事件引导的模糊合成框架，用于生成多样的训练对，以校准预训练模型至目标域。现有方法受限于运动与视觉内容的固有纠缠，而本文方法利用事件相机的高时间分辨率有效解耦二者，使其不仅能利用给定内容固有的内在运动，还能利用目标域内不同来源的外在运动，从而通过微调实现有效自适应。具体而言，EvBS包含两种互补策略：内在模糊合成，即用内容自身的运动模式对清晰内容进行模糊处理；外在模糊合成，即将模糊块的运动迁移至不同的清晰内容。该方法生成的多样训练对打破了运动与内容自然耦合的固有约束，提升了域自适应去模糊性能。在多个基准上开展的大量实验表明，EvBS可有效增强现有去模糊模型在未见测试数据集上的鲁棒性。
英文摘要
Motion deblurring has achieved remarkable progress with deep learning, yet pre-trained deblurring models often suffer from performance degradation in real-world scenarios due to the domain shift between training and testing distributions. To remedy this, we propose EvBS, an event-guided blur synthesis framework that generates diverse training pairs for calibrating pre-trained models to the target domain. While existing methods are constrained by the inherent entanglement between motion and visual content, our method leverages the high temporal resolution of event cameras to effectively decouple them. This enables us to utilize not only the intrinsic motion that is inherent to the given content but also extrinsic motion transferred from different sources within the target domain, thereby facilitating effective adaptation via fine-tuning. Specifically, EvBS comprises two complementary strategies: Intrinsic-Blur Synthesis, which blurs sharp contents with their own motion patterns, and Extrinsic-Blur Synthesis, which transfers motion from blurry patches to distinct sharp content. This approach generates a diverse set of training pairs that break the inherent constraints of naturally coupled motion and content, resulting in enhanced domain-adaptive deblurring performance. Extensive experiments on multiple benchmarks demonstrate that EvBS effectively enhances the robustness of existing deblurring models on unseen testing datasets.
CommentsAccepted to ACM Multimedia 2026 (ACM MM 2026)
