Problem
Research questions and friction points this paper is trying to address.
Real-Time Video Deblurring
Motion Blur
Camera Shake
Edge Devices
Computational Efficiency
TSRN-RTVD: Real-Time Video Deblurring System
🤖 AI Summary
This study addresses the challenge of balancing high-quality video deblurring with real-time performance on consumer-grade hardware by proposing an efficient deblurring system guided by camera trajectory reconstruction. The core innovation lies in explicitly converting physical motion signals into restoration priors and integrating them with a lightweight neural network architecture, effectively overcoming the computational complexity bottleneck of conventional methods. Additionally, a real-time visual interactive scheme is designed to enhance practical usability. Experimental results demonstrate that the proposed method achieves a PSNR of 30.08 dB on the GoPro dataset while enabling real-time processing at 30 FPS on a single consumer GPU. This work provides an efficient solution for high-performance video restoration on edge devices.
📝 Abstract
As video capture moves to handheld and edge devices, motion blur from camera shake has become a pervasive degradation that lowers perceptual quality and harms downstream vision tasks. The strongest deblurring networks recover impressive detail, yet they remain computationally heavy and overwhelmingly complex, so their quality comes at a cost that consumer hardware cannot pay in real time. This gap between restoration quality and on-device speed is exactly what makes real-time deblurring difficult.
We developed and implemented TSRN-RTVD, an efficient video deblurring system that explicitly reconstructs the underlying camera trajectory during exposure and uses the recovered motion to guide restoration. This approach turns the physical cause of blur into a signal that drives sharpening. Our system runs on a single consumer GPU and restores the video at 30 FPS while reaching 30.08 dB PSNR on the GoPro dataset. We demonstrate TSRN-RTVD on consumer devices with interactive side-by-side visualization of the blurry input and the deblurred output, live throughput, and an on-screen view of the recovered camera trajectory. Demo video is available at https://youtu.be/3alMwVrVALU.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Real-Time Video Deblurring
Camera Trajectory Reconstruction
Motion-Guided Restoration
Edge Devices
Efficient Network
🔎 Similar Papers
No similar papers found.
