Single-pixel imaging (SPI) is a potential computational imaging technique
which produces image by solving an illposed reconstruction problem from few
measurements captured by a single-pixel detector. Deep learning has achieved
impressive success on SPI reconstruction. However, previous poor reconstruction
performance and impractical imaging model limit its real-world applications. In
this paper, we propose a deep unfolding network with hybrid-attention
Transformer on Kronecker SPI model, dubbed HATNet, to improve the imaging
quality of real SPI cameras. Specifically, we unfold the computation graph of
the iterative shrinkagethresholding algorithm (ISTA) into two alternative
modules: efficient tensor gradient descent and hybrid-attention multiscale
denoising. By virtue of Kronecker SPI, the gradient descent module can avoid
high computational overheads rooted in previous gradient descent modules based
on vectorized SPI. The denoising module is an encoder-decoder architecture
powered by dual-scale spatial attention for high- and low-frequency aggregation
and channel attention for global information recalibration. Moreover, we build
a SPI prototype to verify the effectiveness of the proposed method. Extensive
experiments on synthetic and real data demonstrate that our method achieves the
state-of-the-art performance. The source code and pre-trained models are
available at this https URL

通过使用深度展开网络和混合注意力 Transformer 解决 Kronecker SPI 模型的问题，我们提出了一种名为 HATNet 的方法，可以改善真实 SPI 相机的成像质量，并在合成和真实数据上进行了广泛实验证明方法达到了最先进的性能。

用于大规模单像素成像的双尺度 Transformer

Dual-Scale Transformer for Large-Scale Single-Pixel Imaging

A physics-driven generative adversarial network (GAN) was established here
for single-pixel hyperspectral imaging (HSI) in the infrared spectrum, to
eliminate the extensive data training work required by traditional data-driven
model. Within the GAN framework, the physical process of single-pixel imaging
(SPI) was integrated into the generator, and the actual and estimated
one-dimensional (1D) bucket signals were employed as constraints in the
objective function to update the network's parameters and optimize the
generator with the assistance of the discriminator. In comparison to
single-pixel infrared HSI methods based on compressed sensing and
physics-driven convolution neural networks, our physics-driven GAN-based
single-pixel infrared HSI can achieve higher imaging performance but with fewer
measurements. We believe that this physics-driven GAN will promote practical
applications of computational imaging, especially various SPI-based techniques.

通过物理驱动型生成对抗网络（GAN），整合了单像素红外高光谱成像（HSI）的物理过程，并利用真实和估计的一维桶信号作为目标函数的约束条件来更新网络参数并优化生成器，从而实现了更高的成像性能但需要更少的测量次数。我们相信这一物理驱动型 GAN 将促进计算成像，特别是各种基于单像素成像技术的实际应用。

以物理推动的生成对抗网络赋能单像素红外高光谱成像

Physics-driven generative adversarial networks empower single-pixel  infrared hyperspectral imaging

Single-pixel imaging (SPI) is a novel optical imaging technique by replacing
a two-dimensional pixelated sensor with a single-pixel detector and pattern
illuminations. SPI have been extensively used for various tasks related to
image acquisition and processing. In this work, a novel non-image-based task of
playing Tic-Tac-Toe games interactively is merged into the framework of SPI. An
optoelectronic artificial intelligent (AI) player with minimal digital
computation can detect the game states, generate optimal moves and display
output results mainly by pattern illumination and single-pixel detection.
Simulated and experimental results demonstrate the feasibility of proposed
scheme and its unbeatable performance against human players.

该研究提出了一种基于单像素成像技术的新方法，在光电人工智能玩家的帮助下，通过图案照明和单像素检测实现了与人进行互动的井字棋游戏，并展示了其在实验中的可行性和对人类玩家无法击败的表现。