# Deep Amended Gradient Descent for Efficient Spectral Reconstruction from Single RGB Images

arXiv: https://arxiv.org/abs/2108.05547 · HTML: https://mlsanity.com/paper/2108.05547/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 73 references that are in the map.
- First posted on arXiv 12 Aug 2021.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processing](https://mlsanity.com/paper/1912.10557/) (2019)
- [Deep Plug-and-Play Super-Resolution for Arbitrary Blur Kernels](https://mlsanity.com/paper/1903.12529/) (2019)
- [Material Based Object Tracking in Hyperspectral Videos: Benchmark and Algorithms](https://mlsanity.com/paper/1812.04179/) (2018)
- [Multispectral and Hyperspectral Image Fusion by MS/HS Fusion Net](https://mlsanity.com/paper/1901.03281/) (2019)
- [Weighted Low-rank Tensor Recovery for Hyperspectral Image Restoration](https://mlsanity.com/paper/1709.00192/) (2017)
- [NTIRE 2020 Challenge on Spectral Reconstruction from an RGB Image](https://mlsanity.com/paper/2005.03412/) (2020)
- [Hierarchical Regression Network for Spectral Reconstruction from RGB Images](https://mlsanity.com/paper/2005.04703/) (2020)
- [AdaptiveWeighted Attention Network with Camera Spectral Sensitivity Prior for Spectral Reconstruction from RGB Images](https://mlsanity.com/paper/2005.09305/) (2020)
- [Cross-Attention in Coupled Unmixing Nets for Unsupervised Hyperspectral Super-Resolution](https://mlsanity.com/paper/2007.05230/) (2020)
- [Unsupervised Sparse Dirichlet-Net for Hyperspectral Image Super-Resolution](https://mlsanity.com/paper/1804.05042/) (2018)
- [Learned Spectral Super-Resolution](https://mlsanity.com/paper/1703.09470/) (2017)
- [Validating Hyperspectral Image Segmentation](https://mlsanity.com/paper/1811.03707/) (2018)
- [Pixel-aware Deep Function-mixture Network for Spectral Super-Resolution](https://mlsanity.com/paper/1903.10501/) (2019)
- [Hyperspectral Image Super-resolution via Deep Progressive Zero-centric Residual Learning](https://mlsanity.com/paper/2006.10300/) (2020)
- [Adversarial Networks for Spatial Context-Aware Spectral Image Reconstruction from RGB](https://mlsanity.com/paper/1709.00265/) (2017)
- [Spectral Superresolution of Multispectral Imagery with Joint Sparse and Low-Rank Learning](https://mlsanity.com/paper/2007.14006/) (2020)
- [Towards Spectral Estimation from a Single RGB Image in the Wild](https://mlsanity.com/paper/1812.00805/) (2018)
- [Fast Hyperspectral Image Recovery via Non-iterative Fusion of Dual-Camera Compressive Hyperspectral Imaging](https://mlsanity.com/paper/2012.15104/) (2020)

## Built on by (most cited first, 7 of 7)

- [Deep Posterior Distribution-based Embedding for Hyperspectral Image Super-resolution](https://mlsanity.com/paper/2205.14887/) (2022)
- [GMSR:Gradient-Guided Mamba for Spectral Reconstruction from RGB Images](https://mlsanity.com/paper/2405.07777/) (2024)
- [HPRN: Holistic Prior-embedded Relation Network for Spectral Super-Resolution](https://mlsanity.com/paper/2112.14608/) (2021)
- [AI-Driven HSI: Multimodality, Fusion, Challenges, and the Deep Learning Revolution](https://mlsanity.com/paper/2502.06894/) (2025)
- [M3SR: Multi-Scale Multi-Perceptual Mamba for Efficient Spectral Reconstruction](https://mlsanity.com/paper/2601.08293/) (2026)
- [Model-Guided Network with Cluster-Based Operators for Spatio-Spectral Super-Resolution](https://mlsanity.com/paper/2505.24605/) (2025)
- [MCGA: Mixture of Codebooks Hyperspectral Reconstruction via Grayscale-Aware Attention](https://mlsanity.com/paper/2507.09885/) (2025)

## Abstract (arXiv)

This paper investigates the problem of recovering hyperspectral (HS) images from single RGB images. To tackle such a severely ill-posed problem, we propose a physically-interpretable, compact, efficient, and end-to-end learning-based framework, namely AGD-Net. Precisely, by taking advantage of the imaging process, we first formulate the problem explicitly based on the classic gradient descent algorithm. Then, we design a lightweight neural network with a multi-stage architecture to mimic the formed amended gradient descent process, in which efficient convolution and novel spectral zero-mean normalization are proposed to effectively extract spatial-spectral features for regressing an initialization, a basic gradient, and an incremental gradient. Besides, based on the approximate low-rank property of HS images, we propose a novel rank loss to promote the similarity between the global structures of reconstructed and ground-truth HS images, which is optimized with our singular value weighting strategy during training. Moreover, AGD-Net, a single network after one-time training, is flexible to handle the reconstruction with various spectral response functions. Extensive experiments over three commonly-used benchmark datasets demonstrate that AGD-Net can improve the reconstruction quality by more than 1.0 dB on average while saving 67× parameters and 32× FLOPs, compared with state-of-the-art methods. The code will be publicly available at https://github.com/zbzhzhy/GD-Net.