Joint Optimization of Hadamard Sensing and Reconstruction in Compressed Sensing Fluorescence Microscopy

Hadamard单像素成像中一种细节增强的采样策略

A detail-enhanced sampling strategy in Hadamard single-pixel imaging

本文提出一种基于指数概率采样和XY顺序的Hadamard单像素成像方法，在极少采样下结合压缩感知实现高效重建，并有效保留图像边缘与细节。

学习型单像素荧光显微术

Learned Single-Pixel Fluorescence Microscopy

本文提出自监督学习的自编码器以联合优化单像素荧光显微成像的测量矩阵与重建网络，在真实多光谱和强度数据上实现百倍提速、更高画质及低成本多光谱成像。

Super sub-Nyquist single-pixel imaging by means of cake-cutting Hadamard basis sort

Single-pixel imaging via compressed sensing can reconstruct high-quality images from a few linear random measurements of an object/scene known a priori to be sparse or compressive, by using a point/bucket detector without spatial resolution. Nevertheless, it still faces a harsh trade-off among the acquisition time, the spatial resolution and the signal-to-noise ratio. Here we present a new compressive imaging approach with use of a strategy called cake-cutting which optimally reorders the deterministic Hadamard basis. By this means, the number of measurements can be dramatically reduced by mor…

High-speed Millimeter-wave 5G/6G Image Transmission via Artificial Intelligence

Artificial Intelligence (AI) has been used to jointly optimize a mmWave Compressed Sensing (CS) for high-speed 5G/6G image transmission. Specifically, we have developed a Dictionary Learning Compressed Sensing neural Network (DL-CSNet) to realize three key functionalities: 1) to learn the dictionary basis of the images for transmission; 2) to optimize the Hadamard measurement matrix; and 3) to reconstruct the lossless images with the learned dictionary basis. A 94-GHz prototype has been built and up to one order of image transmission speed increase has been realized for letters ``A" to ``Z".

Dual-space Compressed Sensing

Compressed sensing (CS) is a powerful method routinely employed to accelerate image acquisition. It is particularly suited to situations when the image under consideration is sparse but can be sampled in a basis where it is non-sparse. Here we propose an alternate CS regime in situations where the image can be sampled in two incoherent spaces simultaneously, with a special focus on image sampling in Fourier reciprocal spaces (e.g. real-space and k-space). Information is fed-forward from one space to the other, allowing new opportunities to efficiently solve the optimization problem at the hear…

压缩循环神经网络以用于荧光寿命成像中的 FPGA 加速实现

Compressing Recurrent Neural Networks for FPGA-accelerated Implementation in Fluorescence Lifetime Imaging

本文针对 FLI 实时分析在 FPGA 上部署 RNN 的资源限制，评估权重缩减、KD、PTQ 与 QAT，提出 Seq2SeqLite，在 8 位精度下以 98% 参数压缩保持性能。