FRN: Fractal-Based Recursive Spectral Reconstruction Network
- URL: http://arxiv.org/abs/2505.15439v1
- Date: Wed, 21 May 2025 12:20:59 GMT
- Title: FRN: Fractal-Based Recursive Spectral Reconstruction Network
- Authors: Ge Meng, Zhongnan Cai, Ruizhe Chen, Jingyan Tu, Yingying Wang, Yue Huang, Xinghao Ding,
- Abstract summary: spectral reconstruction can significantly reduce the cost of hyperspectral images (HSIs) from RGB images.<n>We propose a Fractal-Based Recursive Spectral Reconstruction Network (FRN) which treats spectral reconstruction as a progressive process.<n> FRN achieves superior reconstruction performance compared to state-of-the-art methods in both quantitative and qualitative evaluations.
- Score: 32.54705293932158
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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.
Related papers
- Unleashing Correlation and Continuity for Hyperspectral Reconstruction from RGB Images [64.80875911446937]
We propose a Correlation and Continuity Network (CCNet) for HSI reconstruction from RGB images.<n>For the correlation of local spectrum, we introduce the Group-wise Spectral Correlation Modeling (GrSCM) module.<n>For the continuity of global spectrum, we design the Neighborhood-wise Spectral Continuity Modeling (NeSCM) module.
arXiv Detail & Related papers (2025-01-02T15:14:40Z) - Contourlet Refinement Gate Framework for Thermal Spectrum Distribution Regularized Infrared Image Super-Resolution [54.293362972473595]
Image super-resolution (SR) aims to reconstruct high-resolution (HR) images from their low-resolution (LR) counterparts.
Current approaches to address SR tasks are either dedicated to extracting RGB image features or assuming similar degradation patterns.
We propose a Contourlet refinement gate framework to restore infrared modal-specific features while preserving spectral distribution fidelity.
arXiv Detail & Related papers (2024-11-19T14:24:03Z) - Spectral-wise Implicit Neural Representation for Hyperspectral Image Reconstruction [13.79887292039637]
Coded Aperture Snapshot Spectral Imaging (CASSI) reconstruction aims to recover the 3D spatial-spectral signal from 2D measurement.<n>Existing methods for reconstructing HSI typically involve learning mappings from a 2D compressed image to a predetermined set of discrete spectral bands.<n>We propose an innovative method called Spectral-wise Implicit Neural Representation (SINR) as a pioneering step toward addressing this limitation.
arXiv Detail & Related papers (2023-12-02T08:06:07Z) - A Scale-Arbitrary Image Super-Resolution Network Using Frequency-domain
Information [42.55177009667711]
Image super-resolution (SR) is a technique to recover lost high-frequency information in low-resolution (LR) images.
In this paper, we study image features in the frequency domain to design a novel scale-arbitrary image SR network.
arXiv Detail & Related papers (2022-12-08T15:10:49Z) - Reconstruction of compressed spectral imaging based on global structure
and spectral correlation [17.35611893815407]
The proposed method uses the convolution kernel to operate the global image.
To solve the problem that convolutional sparse coding is insensitive to low frequency, the global total-variation (TV) constraint is added.
The proposed method improves the reconstruction quality by up to 7 dB in PSNR and 10% in SSIM.
arXiv Detail & Related papers (2022-10-27T14:31:02Z) - Spectral2Spectral: Image-spectral Similarity Assisted Spectral CT Deep
Reconstruction without Reference [5.109423491004876]
We propose an iterative deep reconstruction network to synergize unsupervised method and data priors into a unified framework, named as Spectral2Spectral.
Our Spectral2Spectral employs an unsupervised deep training strategy to obtain high-quality images from noisy data in an end-to-end fashion.
Three large-scale preclinical datasets experiments demonstrate that the Spectral2spectral reconstructs better image quality than other the state-of-the-art methods.
arXiv Detail & Related papers (2022-10-03T03:07:33Z) - Towards performant and reliable undersampled MR reconstruction via
diffusion model sampling [67.73698021297022]
DiffuseRecon is a novel diffusion model-based MR reconstruction method.
It guides the generation process based on the observed signals.
It does not require additional training on specific acceleration factors.
arXiv Detail & Related papers (2022-03-08T02:25:38Z) - Continuous Spectral Reconstruction from RGB Images via Implicit Neural
Representation [43.622087181097164]
Existing methods for spectral reconstruction usually learn a discrete mapping from RGB images to a number of spectral bands.
We propose Neural Spectral Reconstruction (NeSR) to lift this limitation, by introducing a novel continuous spectral representation.
NeSR extends the flexibility of spectral reconstruction by enabling an arbitrary number of spectral bands as the target output.
arXiv Detail & Related papers (2021-12-24T09:08:23Z) - Tuning IR-cut Filter for Illumination-aware Spectral Reconstruction from
RGB [84.1657998542458]
It has been proven that the reconstruction accuracy relies heavily on the spectral response of the RGB camera in use.
This paper explores the filter-array based color imaging mechanism of existing RGB cameras, and proposes to design the IR-cut filter properly for improved spectral recovery.
arXiv Detail & Related papers (2021-03-26T19:42:21Z) - Non-local Meets Global: An Iterative Paradigm for Hyperspectral Image
Restoration [66.68541690283068]
We propose a unified paradigm combining the spatial and spectral properties for hyperspectral image restoration.
The proposed paradigm enjoys performance superiority from the non-local spatial denoising and light computation complexity.
Experiments on HSI denoising, compressed reconstruction, and inpainting tasks, with both simulated and real datasets, demonstrate its superiority.
arXiv Detail & Related papers (2020-10-24T15:53:56Z) - Learning Spatial-Spectral Prior for Super-Resolution of Hyperspectral
Imagery [79.69449412334188]
In this paper, we investigate how to adapt state-of-the-art residual learning based single gray/RGB image super-resolution approaches.
We introduce a spatial-spectral prior network (SSPN) to fully exploit the spatial information and the correlation between the spectra of the hyperspectral data.
Experimental results on some hyperspectral images demonstrate that the proposed SSPSR method enhances the details of the recovered high-resolution hyperspectral images.
arXiv Detail & Related papers (2020-05-18T14:25:50Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.