# From Less to More: Spectral Splitting and Aggregation Network for Hyperspectral Face Super-Resolution

arXiv: https://arxiv.org/abs/2108.13584 · HTML: https://mlsanity.com/paper/2108.13584/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 60 references that are in the map.
- First posted on arXiv 31 Aug 2021.

## Builds on (most cited first, 18 of 18)

- [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)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Progressive Neural Architecture Search](https://mlsanity.com/paper/1712.00559/) (2017)
- [Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution](https://mlsanity.com/paper/1704.03915/) (2017)
- [FSRNet: End-to-End Learning Face Super-Resolution with Facial Priors](https://mlsanity.com/paper/1711.10703/) (2017)
- [Hyperspectral pansharpening: a review](https://mlsanity.com/paper/1504.04531/) (2015)
- [Learning Spatial-Spectral Prior for Super-Resolution of Hyperspectral Imagery](https://mlsanity.com/paper/2005.08752/) (2020)
- [Deep Cascaded Bi-Network for Face Hallucination](https://mlsanity.com/paper/1607.05046/) (2016)
- [Deep Hyperspectral Prior: Denoising, Inpainting, Super-Resolution](https://mlsanity.com/paper/1902.00301/) (2019)
- [Multispectral and Hyperspectral Image Fusion by MS/HS Fusion Net](https://mlsanity.com/paper/1901.03281/) (2019)
- [Attention-Aware Face Hallucination via Deep Reinforcement Learning](https://mlsanity.com/paper/1708.03132/) (2017)
- [Deep Learning-based Face Super-Resolution: A Survey](https://mlsanity.com/paper/2101.03749/) (2021)
- [Learning to Hallucinate Face Images via Component Generation and Enhancement](https://mlsanity.com/paper/1708.00223/) (2017)
- [Face Hallucination using Linear Models of Coupled Sparse Support](https://mlsanity.com/paper/1512.06009/) (2015)
- [Super-Resolution for Hyperspectral and Multispectral Image Fusion Accounting for Seasonal Spectral Variability](https://mlsanity.com/paper/1808.10072/) (2018)

## Built on by (most cited first, 1 of 1)

- [SpectralNeRF: Physically Based Spectral Rendering with Neural Radiance Field](https://mlsanity.com/paper/2312.08692/) (2023)

## Abstract (arXiv)

High-resolution (HR) hyperspectral face image plays an important role in face related computer vision tasks under uncontrolled conditions, such as low-light environment and spoofing attacks. However, the dense spectral bands of hyperspectral face images come at the cost of limited amount of photons reached a narrow spectral window on average, which greatly reduces the spatial resolution of hyperspectral face images. In this paper, we investigate how to adapt the deep learning techniques to hyperspectral face image super-resolution (HFSR), especially when the training samples are very limited. Benefiting from the amount of spectral bands, in which each band can be seen as an image, we present a spectral splitting and aggregation network (SSANet) for HFSR with limited training samples. In the shallow layers, we split the hyperspectral image into different spectral groups. Then, we gradually aggregate the neighbor bands at deeper layers to exploit spectral correlations. By this spectral splitting and aggregation strategy (SSAS), we can divide the original hyperspectral image into multiple samples (from less to more) to support the efficient training of the network and effectively exploit the spectral correlations among spectrum. To cope with the challenge of small training sample size (S3) problem, we propose to expand the training samples by a self-representation model and symmetry-induced augmentation. Experiments show that SSANet can well model the joint correlations of spatial and spectral information. By expanding the training samples, SSANet can effectively alleviate the S3 problem.