SSG-GAN: spatial-spectral guided generative adversarial network for hyperspectral reconstruction from RGB images
Hyperspectral reconstruction from a single RGB image provides a practical and low-cost solution for spectral imaging with conventional cameras. However, the task is highly ill-posed because three broad RGB channels must be mapped to multiple continuous narrow spectral bands. Existing methods, including convolutional, Transformer-based, multi-scale, and adversarial reconstruction models, have improved reconstruction accuracy, but many of them still learn RGB spatial structures and hyperspectral reconstruction features in a coupled reconstruction stream, while adversarial constraints mainly focus on spatial distributions. To address these issues, we propose SSG-GAN, a spatially guided hyperspectral reconstruction framework. The generator explicitly decouples RGB spatial-prior extraction from hyperspectral reconstruction through a dedicated multi-scale guidance branch. At corresponding decoding stages, a Cross-Branch Spatial-Spectral Attention (CB-SSA) module uses guidance-derived spatial weights to modulate reconstruction features and further refines them through feature-channel modulation and channel recalibration. Moreover, the discriminator incorporates a dedicated pixel-wise spectral-vector branch to evaluate joint band responses, providing complementary adversarial supervision alongside the multi-scale spatial branches. Experiments on CAVE, Harvard, and ICVL demonstrate the competitive performance of SSG-GAN. Specifically, it achieves MRAE/SAM/RMSE values of 0.0605/0.0734/0.0177 on CAVE, 0.0393/0.0294/0.0041 on Harvard, and 0.0303/0.0309/0.00101 on ICVL.
Authors
- Xiaoxia Xiao (ORCID: https://orcid.org/0009-0007-4759-284X)
- Sixiang Quan
- Jun Liu (ORCID: https://orcid.org/0000-0002-7280-1443)
- Tai Zhang (ORCID: https://orcid.org/0009-0001-8002-7902)
- Xian Cao
- Yingying Peng
- Xianlong Tang
- Huali Li
- Zhihui Wang
- Chenxin Zhang
Institutions
- Hunan University of Traditional Chinese Medicine (CN)
- Hunan University (CN)
Publication Details
- Journal
- Scientific Reports
- Published
- 2026-11-16
- DOI
- https://doi.org/10.1038/s41598-026-80321-7
- Primary Topic
- Remote-Sensing Image Classification
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China
- Natural Science Foundation of Hunan Province
- Hunan University of Chinese Medicine