计算机科学
人工智能
快照(计算机存储)
循环神经网络
计算机视觉
压缩传感
卷积神经网络
迭代重建
残余物
深度学习
模式识别(心理学)
人工神经网络
解码方法
稳健性(进化)
带宽(计算)
医学影像学
图像复原
数据压缩
词典学习
帧速率
作者
Ziheng Cheng,Bo Chen,Ruiying Lu,Zhengjue Wang,Hao Zhang,Ziyi Meng,Xin Yuan
标识
DOI:10.1109/tpami.2022.3161934
摘要
Conventional high-speed and spectral imaging systems are expensive and they usually consume a significant amount of memory and bandwidth to save and transmit the high-dimensional data. By contrast, snapshot compressive imaging (SCI), where multiple sequential frames are coded by different masks and then summed to a single measurement, is a promising idea to use a 2-dimensional camera to capture 3-dimensional scenes. In this paper, we consider the reconstruction problem in SCI, i.e., recovering a series of scenes from a compressed measurement. Specifically, the measurement and modulation masks are fed into our proposed network, dubbed BIdirectional Recurrent Neural networks with Adversarial Training (BIRNAT) to reconstruct the desired frames. BIRNAT employs a deep convolutional neural network with residual blocks and self-attention to reconstruct the first frame, based on which a bidirectional recurrent neural network is utilized to sequentially reconstruct the following frames. Moreover, we build an extended BIRNAT-color algorithm for color videos aiming at joint reconstruction and demosaicing. Extensive results on both video and spectral, simulation and real data from three SCI cameras demonstrate the superior performance of BIRNAT.
科研通智能强力驱动
Strongly Powered by AbleSci AI