LSHR-Net: a hardware-friendly solution for high-resolution computational imaging using a mixed-weights neural network
This work addresses hardware deployment challenges in computational imaging, offering a more efficient solution for applications like digital micromirror devices, though it is incremental in improving existing neural network methods.
The authors tackled the problem of deploying neural-network-based computational imaging on hardware by proposing a mixed-weights neural network with learned binary-weight sensing patterns and a recursive structure, achieving state-of-the-art reconstruction accuracy on benchmark datasets while reducing measurements and computation.
Recent work showed neural-network-based approaches to reconstructing images from compressively sensed measurements offer significant improvements in accuracy and signal compression. Such methods can dramatically boost the capability of computational imaging hardware. However, to date, there have been two major drawbacks: (1) the high-precision real-valued sensing patterns proposed in the majority of existing works can prove problematic when used with computational imaging hardware such as a digital micromirror sampling device and (2) the network structures for image reconstruction involve intensive computation, which is also not suitable for hardware deployment. To address these problems, we propose a novel hardware-friendly solution based on mixed-weights neural networks for computational imaging. In particular, learned binary-weight sensing patterns are tailored to the sampling device. Moreover, we proposed a recursive network structure for low-resolution image sampling and high-resolution reconstruction scheme. It reduces both the required number of measurements and reconstruction computation by operating convolution on small intermediate feature maps. The recursive structure further reduced the model size, making the network more computationally efficient when deployed with the hardware. Our method has been validated on benchmark datasets and achieved the state of the art reconstruction accuracy. We tested our proposed network in conjunction with a proof-of-concept hardware setup.