Real-Time Video Deblurring via Lightweight Motion Compensation
This enables real-time video deblurring for applications like video processing and streaming, though it is incremental as it builds on existing motion compensation and deblurring methods.
The paper tackles the computational overhead of combining motion compensation with video deblurring by proposing a lightweight multi-task unit that integrates both tasks efficiently, achieving state-of-the-art deblurring quality at real-time speeds (30.99dB@30fps on the DVD dataset).
While motion compensation greatly improves video deblurring quality, separately performing motion compensation and video deblurring demands huge computational overhead. This paper proposes a real-time video deblurring framework consisting of a lightweight multi-task unit that supports both video deblurring and motion compensation in an efficient way. The multi-task unit is specifically designed to handle large portions of the two tasks using a single shared network, and consists of a multi-task detail network and simple networks for deblurring and motion compensation. The multi-task unit minimizes the cost of incorporating motion compensation into video deblurring and enables real-time deblurring. Moreover, by stacking multiple multi-task units, our framework provides flexible control between the cost and deblurring quality. We experimentally validate the state-of-the-art deblurring quality of our approach, which runs at a much faster speed compared to previous methods, and show practical real-time performance (30.99dB@30fps measured in the DVD dataset).