轻量级模型RT-Focuser实现边缘设备实时去模糊，兼顾速度与清晰度。
RT-Focuser: A Real-Time Lightweight Model for Edge-side Image Deblurring
- 采用U型结构与三组件设计，提升边缘端特征提取效率。
- 仅5.85M参数下达30.67 dB PSNR，每帧处理仅需6ms。
- 适合自动驾驶、无人机等对延迟敏感的实时视觉场景。
由相机或物体运动引起的运动模糊严重降低图像质量，给自动驾驶、无人机感知和医学成像等实时应用带来挑战。本文提出一种专为实时去模糊设计的轻量级U型网络——RT-Focuser。为平衡速度与精度，设计三个核心模块：用于边缘感知特征提取的轻量级去模糊块（LD）、用于编码器融合的多层级集成聚合模块（MLIA），以及用于解码器渐进优化的跨源融合块（X-Fuse）。在单张模糊输入下训练，RT-Focuser达到30.67 dB PSNR，仅需5.85M参数和15.76 GMACs。在GPU和移动端均实现每帧6ms处理时间，运行速度超过140 FPS，展现出强大的边缘部署潜力。官方代码及使用说明详见：https://github.com/ReaganWu/RT-Focuser。
原文摘要 · Abstract (English)
Motion blur caused by camera or object movement severely degrades image quality and poses challenges for real-time applications such as autonomous driving, UAV perception, and medical imaging. In this paper, a lightweight U-shaped network tailored for real-time deblurring is presented and named RT-Focuser. To balance speed and accuracy, we design three key components: Lightweight Deblurring Block (LD) for edge-aware feature extraction, Multi-Level Integrated Aggregation module (MLIA) for encoder integration, and Cross-source Fusion Block (X-Fuse) for progressive decoder refinement. Trained on a single blurred input, RT-Focuser achieves 30.67 dB PSNR with only 5.85M parameters and 15.76 GMACs. It runs 6ms per frame on GPU and mobile, exceeds 140 FPS on both, showing strong potential for deployment on the edge. The official code and usage are available on: https://github.com/ReaganWu/RT-Focuser.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。