Speed, generalizability, and robustness are fundamental issues for building lightweight computational cameras. Here we demonstrate generalizable image reconstruction with the simplest of hybrid machine vision systems: linear optical preprocessors combined with no-hidden-layer, “small-brain” neural networks. Surprisingly, such simple neural networks are capable of learning the image reconstruction from a range of coded diffraction patterns using two masks. We investigate the possibility of generalized or “universal training” with these small brains. Neural networks trained with sinusoidal or random patterns uniformly distribute errors around a reconstructed image, whereas models trained with a combination of sharp and curved shapes (the phase pattern of optical vortices) reconstruct edges more boldly. We illustrate variable convergence of these simple neural networks and relate learnability of an image to its singular value decomposition entropy of the image. We also provide heuristic experimental results. With thresholding, we achieve robust reconstruction of various disjoint datasets. Our work is favorable for future real-time low size, weight, and power hybrid vision: we reconstruct images on a 15 W laptop CPU with 15,000 frames per second: faster by a factor of 3 than previously reported results and 3 orders of magnitude faster than convolutional neural networks.

中文翻译：

---

面向具有通用训练的简单、可推广的神经网络，用于低 SWaP 混合视觉

速度、通用性和鲁棒性是构建轻量级计算相机的基本问题。在这里，我们展示了使用最简单的混合机器视觉系统的通用图像重建：线性光学预处理器与无隐藏层的“小脑”神经网络相结合。令人惊讶的是，这种简单的神经网络能够使用两个掩码从一系列编码衍射图案中学习图像重建。我们研究了用这些小大脑进行广义或“通用训练”的可能性。使用正弦或随机模式训练的神经网络在重建图像周围均匀分布误差，而使用尖锐和弯曲形状（光学涡旋的相位模式）组合训练的模型更大胆地重建边缘。我们说明了这些简单神经网络的可变收敛性，并将图像的可学习性与图像的奇异值分解熵联系起来。我们还提供启发式实验结果。通过阈值处理，我们实现了各种不相交数据集的稳健重建。我们的工作有利于未来的实时小尺寸、重量和功率混合视觉：我们在 15 W 笔记本电脑 CPU 上以每秒 15,000 帧的速度重建图像：比之前报告的结果快 3 倍，快 3 个数量级比卷积神经网络。