用超材料透镜实现无训练的医学成像，压缩比达0.6%仍保高精度
Computed tomography using meta-optics
- 基于超材料实现无需训练的Radon变换光学成像
- 压缩比0.6%下重建图像质量高，分类准确率达90%
- 适合低功耗、低延迟的医疗影像实时处理场景
计算机视觉任务需处理海量数据以完成图像分类、分割和特征提取。光学预处理器有望减少浮点运算量，实现低功耗与低延迟。然而现有光学预处理器多为学习型，严重依赖训练数据，通用性差。本文提出一种超材料成像系统，实现无需训练的Radon变换。通过同时代数重建技术，实现了0.6%压缩比下的高质量图像重建。在实验测量的Radon数据集上，使用数字变换图像训练的神经网络实现90%分类准确率。
原文摘要 · Abstract (English)
Computer vision tasks require processing large amounts of data to perform image classification, segmentation, and feature extraction. Optical preprocessors can potentially reduce the number of floating point operations required by computer vision tasks, enabling low-power and low-latency operation. However, existing optical preprocessors are mostly learned and hence strongly depend on the training data, and thus lack universal applicability. In this paper, we present a metaoptic imager, which implements the Radon transform obviating the need for training the optics. High quality image reconstruction with a large compression ratio of 0.6% is presented through the use of the Simultaneous Algebraic Reconstruction Technique. Image classification with 90% accuracy is presented on an experimentally measured Radon dataset through neural network trained on digitally transformed images.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。