End-to-End Video Compressive Sensing Using Anderson-Accelerated Unrolled Networks
Type
Conference PaperKAUST Department
Computational Imaging GroupComputer Science Program
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Electrical Engineering
Visual Computing Center (VCC)
Date
2020-06-02Online Publication Date
2020-06-02Print Publication Date
2020-04Permanent link to this record
http://hdl.handle.net/10754/663826
Metadata
Show full item recordAbstract
Compressive imaging systems with spatial-temporal encoding can be used to capture and reconstruct fast-moving objects. The imaging quality highly depends on the choice of encoding masks and reconstruction methods. In this paper, we present a new network architecture to jointly design the encoding masks and the reconstruction method for compressive high-frame-rate imaging. Unlike previous works, the proposed method takes full advantage of denoising prior to provide a promising frame reconstruction. The network is also flexible enough to optimize full-resolution masks and efficient at reconstructing frames. To this end, we develop a new dense network architecture that embeds Anderson acceleration, known from numerical optimization, directly into the neural network architecture. Our experiments show the optimized masks and the dense accelerated network respectively achieve 1.5 dB and 1 dB improvements in PSNR without adding training parameters. The proposed method outperforms other state-of-the-art methods both in simulations and on real hardware. In addition, we set up a coded two-bucket camera for compressive high-frame-rate imaging, which is robust to imaging noise and provides promising results when recovering nearly 1,000 frames per second.Citation
Li, Y., Qi, M., Gulve, R., Wei, M., Genov, R., Kutulakos, K. N., & Heidrich, W. (2020). End-to-End Video Compressive Sensing Using Anderson-Accelerated Unrolled Networks. 2020 IEEE International Conference on Computational Photography (ICCP). doi:10.1109/iccp48838.2020.9105237Conference/Event name
2020 IEEE International Conference on Computational Photography (ICCP)ISBN
978-1-7281-5231-8Additional Links
https://ieeexplore.ieee.org/document/9105237/https://ieeexplore.ieee.org/document/9105237/
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9105237
ae974a485f413a2113503eed53cd6c53
10.1109/ICCP48838.2020.9105237