Video Reconstruction from a Single Motion Blurred Image using Learned Dynamic Phase Coding
This addresses the problem of enhancing camera capabilities for video reconstruction with simpler, more accessible hardware, though it is incremental over prior hybrid methods.
The paper tackles video reconstruction from a single motion-blurred image by proposing a hybrid optical-digital method using learned dynamic phase coding in the lens aperture to encode motion trajectories, achieving improved performance with a real-world camera prototype and generating sharp frame bursts at various rates.
Video reconstruction from a single motion-blurred image is a challenging problem, which can enhance the capabilities of existing cameras. Recently, several works addressed this task using conventional imaging and deep learning. Yet, such purely-digital methods are inherently limited, due to direction ambiguity and noise sensitivity. Some works proposed to address these limitations using non-conventional image sensors, however, such sensors are extremely rare and expensive. To circumvent these limitations with simpler means, we propose a hybrid optical-digital method for video reconstruction that requires only simple modifications to existing optical systems. We use a learned dynamic phase-coding in the lens aperture during the image acquisition to encode the motion trajectories, which serve as prior information for the video reconstruction process. The proposed computational camera generates a sharp frame burst of the scene at various frame rates from a single coded motion-blurred image, using an image-to-video convolutional neural network. We present advantages and improved performance compared to existing methods, using both simulations and a real-world camera prototype. We extend our optical coding also to video frame interpolation and present robust and improved results for noisy videos.