High Frame Rate Video Reconstruction Based on an Event Camera

• Published in: IEEE transactions on pattern analysis and machine intelligence 2022-05, Vol.44 (5), p.2519-2533
• Main Authors: Pan, Liyuan, Hartley, Richard, Scheerlinck, Cedric, Liu, Miaomiao, Yu, Xin, Dai, Yuchao
• Format: Article
• Language: English
• Subjects: Active pixel sensors; Blurring; Cameras; Convexity; Data models; Event camera (DAVIS); fibonacci sequence; high temporal resolution reconstruction; Image reconstruction; Image resolution; Image restoration; Lighting; mEDI model; motion blur; Optimization; Pixels; Regularization; Temporal resolution
• ISSN: 0162-8828; 1939-3539; 2160-9292
• DOI: 10.1109/TPAMI.2020.3036667

Event-based cameras measure intensity changes (called ' events ') with microsecond accuracy under high-speed motion and challenging lighting conditions. With the 'active pixel sensor' (APS), the 'Dynamic and Active-pixel Vision Sensor' (DAVIS) allows the simultaneous output of intensity frames and events. However, the output images are captured at a relatively low frame rate and often suffer from motion blur. A blurred image can be regarded as the integral of a sequence of latent images, while events indicate changes between the latent images. Thus, we are able to model the blur-generation process by associating event data to a latent sharp image. Based on the abundant event data alongside a low frame rate, easily blurred images, we propose a simple yet effective approach to reconstruct high-quality and high frame rate sharp videos. Starting with a single blurred frame and its event data from DAVIS, we propose the Event-based Double Integral (EDI) model and solve it by adding regularization terms. Then, we extend it to multiple Event-based Double Integral (mEDI) model to get more smooth results based on multiple images and their events. Furthermore, we provide a new and more efficient solver to minimize the proposed energy model. By optimizing the energy function, we achieve significant improvements in removing blur and the reconstruction of a high temporal resolution video. The video generation is based on solving a simple non-convex optimization problem in a single scalar variable. Experimental results on both synthetic and real datasets demonstrate the superiority of our mEDI model and optimization method compared to the state-of-the-art.