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

arXiv: https://arxiv.org/abs/2404.05001 · HTML: https://mlsanity.com/paper/2404.05001/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 72 references that are in the map.
- First posted on arXiv 7 Apr 2024.

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [Multiscale Vision Transformers](https://mlsanity.com/paper/2104.11227/) (2021)
- [Pre-Trained Image Processing Transformer](https://mlsanity.com/paper/2012.00364/) (2020)
- [Uformer: A General U-Shaped Transformer for Image Restoration](https://mlsanity.com/paper/2106.03106/) (2021)
- [Plug-and-Play ADMM for Image Restoration: Fixed Point Convergence and Applications](https://mlsanity.com/paper/1605.01710/) (2016)
- [TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up](https://mlsanity.com/paper/2102.07074/) (2021)
- [Deep Generalized Unfolding Networks for Image Restoration](https://mlsanity.com/paper/2204.13348/) (2022)
- [Learning Proximal Operators: Using Denoising Networks for Regularizing Inverse Imaging Problems](https://mlsanity.com/paper/1704.03488/) (2017)
- [Rank Minimization for Snapshot Compressive Imaging](https://mlsanity.com/paper/1807.07837/) (2018)
- [Fast Vision Transformers with HiLo Attention](https://mlsanity.com/paper/2205.13213/) (2022)
- [From Denoising to Compressed Sensing](https://mlsanity.com/paper/1406.4175/) (2014)
- [AMP-Net: Denoising based Deep Unfolding for Compressive Image Sensing](https://mlsanity.com/paper/2004.10078/) (2020)
- [Learned D-AMP: Principled Neural Network based Compressive Image Recovery](https://mlsanity.com/paper/1704.06625/) (2017)
- [Group-based Sparse Representation for Image Restoration](https://mlsanity.com/paper/1405.3351/) (2014)
- [Memory-Augmented Deep Unfolding Network for Compressive Sensing](https://mlsanity.com/paper/2110.09766/) (2021)
- [DR2-Net: Deep Residual Reconstruction Network for Image Compressive Sensing](https://mlsanity.com/paper/1702.05743/) (2017)
- [Dual Vision Transformer](https://mlsanity.com/paper/2207.04976/) (2022)
- [Dynamic Path-Controllable Deep Unfolding Network for Compressive Sensing](https://mlsanity.com/paper/2306.16060/) (2023)
- [Optimization-Inspired Cross-Attention Transformer for Compressive Sensing](https://mlsanity.com/paper/2304.13986/) (2023)
- [A Benchmark for Sparse Coding: When Group Sparsity Meets Rank Minimization](https://mlsanity.com/paper/1709.03979/) (2017)
- [Image Compression Based on Compressive Sensing: End-to-End Comparison with JPEG](https://mlsanity.com/paper/1706.01000/) (2017)
- [Computational Imaging and Artificial Intelligence: The Next Revolution of Mobile Vision](https://mlsanity.com/paper/2109.08880/) (2021)
- [Super sub-Nyquist single-pixel imaging by means of cake-cutting Hadamard basis sort](https://mlsanity.com/paper/1903.11175/) (2019)

## Built on by (most cited first, 6 of 6)

- [Hierarchical Separable Video Transformer for Snapshot Compressive Imaging](https://mlsanity.com/paper/2407.11946/) (2024)
- [Unfolding Framework with Complex-Valued Deformable Attention for High-Quality Computer-Generated Hologram Generation](https://mlsanity.com/paper/2508.21657/) (2025)
- [InverseNet: Benchmarking Operator Mismatch and Calibration Across Compressive Imaging Modalities](https://mlsanity.com/paper/2603.04538/) (2026)
- [Compressive sensing inspired self-supervised single-pixel imaging](https://mlsanity.com/paper/2603.29732/) (2026)
- [Deep Probabilistic Unfolding for Quantized Compressive Sensing](https://mlsanity.com/paper/2605.11475/) (2026)
- [The Lift Spectrum: How Measurement-to-Space Adaptivity Shapes Robustness in Image-Free Single-Pixel Sensing](https://mlsanity.com/paper/2607.22077/) (2026)

## Abstract (arXiv)

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 https://github.com/Gang-Qu/HATNet-SPI.