FRN: Fractal-Based Recursive Spectral Reconstruction Network
Not on the map. Why?
Abstract (arXiv)
Generating hyperspectral images (HSIs) from RGB images through spectral reconstruction can significantly reduce the cost of HSI acquisition. In this paper, we propose a Fractal-Based Recursive Spectral Reconstruction Network (FRN), which differs from existing paradigms that attempt to directly integrate the full-spectrum information from the R, G, and B channels in a one-shot manner. Instead, it treats spectral reconstruction as a progressive process, predicting from broad to narrow bands or employing a coarse-to-fine approach for predicting the next wavelength. Inspired by fractals in mathematics, FRN establishes a novel spectral reconstruction paradigm by recursively invoking an atomic reconstruction module. In each invocation, only the spectral information from neighboring bands is used to provide clues for the generation of the image at the next wavelength, which follows the low-rank property of spectral data. Moreover, we design a band-aware state space model that employs a pixel-differentiated scanning strategy at different stages of the generation process, further suppressing interference from low-correlation regions caused by reflectance differences. Through extensive experimentation across different datasets, FRN achieves superior reconstruction performance compared to state-of-the-art methods in both quantitative and qualitative evaluations.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 22 of its 62 references that are in the map. First posted on arXiv 21 May 2025.
Builds on
22 of 62 references.
References · 22
- 2017Squeeze-and-Excitation Networkscited by 4,763
- 2021Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstructioncited by 110
- 2022MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstructioncited by 72
- 2022Coarse-to-Fine Sparse Transformer for Hyperspectral Image Reconstructioncited by 67
- 2022HDNet: High-resolution Dual-domain Learning for Spectral Compressive Imagingcited by 66
- 2022Degradation-Aware Unfolding Half-Shuffle Transformer for Spectral Compressive Imagingcited by 66
- 2021Deep Gaussian Scale Mixture Prior for Spectral Compressive Imagingcited by 58
- 2013Coded aperture compressive temporal imagingcited by 57
- 2025Fractal Generative Modelscited by 44
- 2024Samba: Semantic Segmentation of Remotely Sensed Images with State Space Modelcited by 37
- 2021Self-supervised Neural Networks for Spectral Snapshot Compressive Imagingcited by 35
- 2020AdaptiveWeighted Attention Network with Camera Spectral Sensitivity Prior for Spectral Reconstruction from RGB Imagescited by 29
10 more
- 2022Learning to Generate Realistic Noisy Images via Pixel-level Noise-aware Adversarial Trainingcited by 29
- 2017Learned Spectral Super-Resolutioncited by 19
- 2024Hi-Mamba: Hierarchical Mamba for Efficient Image Super-Resolutioncited by 16
- 2024MambaCSR: Dual-Interleaved Scanning for Compressed Image Super-Resolution With SSMscited by 14
- 2017Aerial Vehicle Tracking by Adaptive Fusion of Hyperspectral Likelihood Mapscited by 13
- 2018Hyperspectral recovery from RGB images using Gaussian Processescited by 13
- 2019Pixel-aware Deep Function-mixture Network for Spectral Super-Resolutioncited by 13
- 2020Spectral Response Function Guided Deep Optimization-driven Network for Spectral Super-resolutioncited by 12
- 2024RemoteDet-Mamba: A Hybrid Mamba-CNN Network for Multi-modal Object Detection in Remote Sensing Imagescited by 7
- 2024Remote Sensing Image Segmentation Using Vision Mamba and Multi-Scale Multi-Frequency Feature Fusioncited by 6
Built on by
Citing papers per year: 2026: 1.
1 paper.