# Pixel Adaptive Deep Unfolding Transformer for Hyperspectral Image Reconstruction

arXiv: https://arxiv.org/abs/2308.10820 · HTML: https://mlsanity.com/paper/2308.10820/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 46 references that are in the map.
- First posted on arXiv 21 Aug 2023.

## Builds on (most cited first, 20 of 20)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [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)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Deep Generalized Unfolding Networks for Image Restoration](https://mlsanity.com/paper/2204.13348/) (2022)
- [Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstruction](https://mlsanity.com/paper/2111.07910/) (2021)
- [Rank Minimization for Snapshot Compressive Imaging](https://mlsanity.com/paper/1807.07837/) (2018)
- [Plug-and-Play Algorithms for Large-scale Snapshot Compressive Imaging](https://mlsanity.com/paper/2003.13654/) (2020)
- [HDNet: High-resolution Dual-domain Learning for Spectral Compressive Imaging](https://mlsanity.com/paper/2203.02149/) (2022)
- [Degradation-Aware Unfolding Half-Shuffle Transformer for Spectral Compressive Imaging](https://mlsanity.com/paper/2205.10102/) (2022)
- [Deep Gaussian Scale Mixture Prior for Spectral Compressive Imaging](https://mlsanity.com/paper/2103.07152/) (2021)
- [GAP-net for Snapshot Compressive Imaging](https://mlsanity.com/paper/2012.08364/) (2020)
- [Hyperspectral Image Denoising Employing a Spatial-Spectral Deep Residual Convolutional Neural Network](https://mlsanity.com/paper/1806.00183/) (2018)
- [A Deep Learning Approach to Structured Signal Recovery](https://mlsanity.com/paper/1508.04065/) (2015)
- [Non-local Meets Global: An Iterative Paradigm for Hyperspectral Image Restoration](https://mlsanity.com/paper/2010.12921/) (2020)
- [Self-supervised Neural Networks for Spectral Snapshot Compressive Imaging](https://mlsanity.com/paper/2108.12654/) (2021)
- [A Trainable Spectral-Spatial Sparse Coding Model for Hyperspectral Image Restoration](https://mlsanity.com/paper/2111.09708/) (2021)
- [HerosNet: Hyperspectral Explicable Reconstruction and Optimal Sampling Deep Network for Snapshot Compressive Imaging](https://mlsanity.com/paper/2112.06238/) (2021)
- [Deep Plug-and-Play Prior for Hyperspectral Image Restoration](https://mlsanity.com/paper/2209.08240/) (2022)
- [Coarse-to-Fine Video Denoising with Dual-Stage Spatial-Channel Transformer](https://mlsanity.com/paper/2205.00214/) (2022)

## Built on by (most cited first, 20 of 20)

- [Real-world Image Dehazing with Coherence-based Pseudo Labeling and Cooperative Unfolding Network](https://mlsanity.com/paper/2406.07966/) (2024)
- [In2SET: Intra-Inter Similarity Exploiting Transformer for Dual-Camera Compressive Hyperspectral Imaging](https://mlsanity.com/paper/2312.13319/) (2023)
- [Dispersed Structured Light for Hyperspectral 3D Imaging](https://mlsanity.com/paper/2311.18287/) (2023)
- [Dual Hyperspectral Mamba for Efficient Spectral Compressive Imaging](https://mlsanity.com/paper/2406.00449/) (2024)
- [Iterative Low-rank Network for Hyperspectral Image Denoising](https://mlsanity.com/paper/2509.00356/) (2025)
- [PCMamba: Physics-Informed Cross-Modal State Space Model for Dual-Camera Compressive Hyperspectral Imaging](https://mlsanity.com/paper/2505.16373/) (2025)
- [Spectral Compressive Imaging via Chromaticity-Intensity Decomposition](https://mlsanity.com/paper/2509.16690/) (2025)
- [LRDUN: A Low-Rank Deep Unfolding Network for Efficient Spectral Compressive Imaging](https://mlsanity.com/paper/2511.18513/) (2025)
- [Learning Exhaustive Correlation for Spectral Super-Resolution: Where Spatial-Spectral Attention Meets Linear Dependence](https://mlsanity.com/paper/2312.12833/) (2023)
- [Self-Supervised One-Step Diffusion Refinement for Snapshot Compressive Imaging](https://mlsanity.com/paper/2409.07417/) (2024)
- [From Image- to Pixel-level: Label-efficient Hyperspectral Image Reconstruction](https://mlsanity.com/paper/2503.06852/) (2025)
- [NukesFormers: Unpaired Hyperspectral Image Generation with Non-Uniform Domain Alignment](https://mlsanity.com/paper/2503.07004/) (2025)
- [Physical Degradation Model-Guided Interferometric Hyperspectral Reconstruction with Unfolding Transformer](https://mlsanity.com/paper/2506.21880/) (2025)
- [Deep Equilibrium Convolutional Sparse Coding for Hyperspectral Image Denoising](https://mlsanity.com/paper/2508.15553/) (2025)
- [Progressive Flow-inspired Unfolding for Spectral Compressive Imaging](https://mlsanity.com/paper/2509.12079/) (2025)
- [Flow-Matching Guided Deep Unfolding for Hyperspectral Image Reconstruction](https://mlsanity.com/paper/2510.01912/) (2025)
- [Hierarchical Spatial-Frequency Aggregation for Spectral Deconvolution Imaging](https://mlsanity.com/paper/2511.06751/) (2025)
- [Efficient Hyperspectral Image Reconstruction Using Lightweight Separate Spectral Transformers](https://mlsanity.com/paper/2601.01064/) (2026)
- [Exploring Spatiotemporal Feature Propagation for Video-Level Compressive Spectral Reconstruction: Dataset, Model and Benchmark](https://mlsanity.com/paper/2603.00611/) (2026)
- [Phy-CoSF: Physics-Guided Continuous Spectral Fields Reconstruction and Super-Resolution for Snapshot Compressive Imaging](https://mlsanity.com/paper/2605.13583/) (2026)

## Abstract (arXiv)

Hyperspectral Image (HSI) reconstruction has made gratifying progress with the deep unfolding framework by formulating the problem into a data module and a prior module. Nevertheless, existing methods still face the problem of insufficient matching with HSI data. The issues lie in three aspects: 1) fixed gradient descent step in the data module while the degradation of HSI is agnostic in the pixel-level. 2) inadequate prior module for 3D HSI cube. 3) stage interaction ignoring the differences in features at different stages. To address these issues, in this work, we propose a Pixel Adaptive Deep Unfolding Transformer (PADUT) for HSI reconstruction. In the data module, a pixel adaptive descent step is employed to focus on pixel-level agnostic degradation. In the prior module, we introduce the Non-local Spectral Transformer (NST) to emphasize the 3D characteristics of HSI for recovering. Moreover, inspired by the diverse expression of features in different stages and depths, the stage interaction is improved by the Fast Fourier Transform (FFT). Experimental results on both simulated and real scenes exhibit the superior performance of our method compared to state-of-the-art HSI reconstruction methods. The code is released at: https://github.com/MyuLi/PADUT.