RT-Focuser: A Real-Time Lightweight Model for Edge-side Image Deblurring
This addresses motion blur degradation for real-time applications like autonomous driving and UAV perception, representing an incremental improvement in lightweight deblurring models.
The paper tackles real-time image deblurring for edge devices by proposing RT-Focuser, a lightweight U-shaped network that achieves 30.67 dB PSNR with 5.85M parameters and runs at over 140 FPS on GPU and mobile.
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.