Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstruction

• URL: http://arxiv.org/abs/2111.07910v1
• Date: Mon, 15 Nov 2021 16:59:48 GMT
• Title: Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstruction
• Authors: Yuanhao Cai, Jing Lin, Xiaowan Hu, Haoqian Wang, Xin Yuan, Yulun Zhang, Radu Timofte, Luc Van Gool
• Abstract summary: Hyperspectral image (HSI) reconstruction aims to recover the 3D spatial-spectral signal from a 2D measurement. Modeling the inter-spectra interactions is beneficial for HSI reconstruction. Mask-guided Spectral-wise Transformer (MST) proposes a novel framework for HSI reconstruction.
• Score: 127.20208645280438
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Hyperspectral image (HSI) reconstruction aims to recover the 3D spatial-spectral signal from a 2D measurement in the coded aperture snapshot spectral imaging (CASSI) system. The HSI representations are highly similar and correlated across the spectral dimension. Modeling the inter-spectra interactions is beneficial for HSI reconstruction. However, existing CNN-based methods show limitations in capturing spectral-wise similarity and long-range dependencies. Besides, the HSI information is modulated by a coded aperture (physical mask) in CASSI. Nonetheless, current algorithms have not fully explored the guidance effect of the mask for HSI restoration. In this paper, we propose a novel framework, Mask-guided Spectral-wise Transformer (MST), for HSI reconstruction. Specifically, we present a Spectral-wise Multi-head Self-Attention (S-MSA) that treats each spectral feature as a token and calculates self-attention along the spectral dimension. In addition, we customize a Mask-guided Mechanism (MM) that directs S-MSA to pay attention to spatial regions with high-fidelity spectral representations. Extensive experiments show that our MST significantly outperforms state-of-the-art (SOTA) methods on simulation and real HSI datasets while requiring dramatically cheaper computational and memory costs.

Related papers

• Empowering Snapshot Compressive Imaging: Spatial-Spectral State Space Model with Across-Scanning and Local Enhancement [51.557804095896174]
  We introduce a State Space Model with Across-Scanning and Local Enhancement, named ASLE-SSM, that employs a Spatial-Spectral SSM for global-local balanced context encoding and cross-channel interaction promoting. Experimental results illustrate ASLE-SSM's superiority over existing state-of-the-art methods, with an inference speed 2.4 times faster than Transformer-based MST and saving 0.12 (M) of parameters.
  arXiv  Detail & Related papers  (2024-08-01T15:14:10Z)
• 3DSS-Mamba: 3D-Spectral-Spatial Mamba for Hyperspectral Image Classification [14.341510793163138]
  We propose a novel 3D-Spectral-Spatial Mamba framework for HSI classification. A 3D-Spectral-Spatial Selective Scanning mechanism is introduced, which performs pixel-wise selective scanning on 3D hyperspectral tokens. Experimental results and analysis demonstrate that the proposed method outperforms the state-of-the-art methods on HSI classification benchmarks.
  arXiv  Detail & Related papers  (2024-05-21T04:10:26Z)
• Spectral-wise Implicit Neural Representation for Hyperspectral Image Reconstruction [14.621504062838731]
  Coded Aperture Snapshot Spectral Imaging (CASSI) reconstruction aims to recover the 3D spatial-spectral signal from 2D measurement. Existing methods for reconstructing HSI typically involve learning mappings from a 2D compressed image to a predetermined set of discrete spectral bands. 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)
• SS-MAE: Spatial-Spectral Masked Auto-Encoder for Multi-Source Remote Sensing Image Classification [35.52272615695294]
  We propose a spatial-spectral masked auto-encoder (SS-MAE) for HSI and LiDAR/SAR data joint classification. Our SS-MAE fully exploits the spatial and spectral representations of the input data. To complement local features in the training stage, we add two lightweight CNNs for feature extraction.
  arXiv  Detail & Related papers  (2023-11-08T03:54:44Z)
• ESSAformer: Efficient Transformer for Hyperspectral Image Super-resolution [76.7408734079706]
  Single hyperspectral image super-resolution (single-HSI-SR) aims to restore a high-resolution hyperspectral image from a low-resolution observation. We propose ESSAformer, an ESSA attention-embedded Transformer network for single-HSI-SR with an iterative refining structure.
  arXiv  Detail & Related papers  (2023-07-26T07:45:14Z)
• Spectral Enhanced Rectangle Transformer for Hyperspectral Image Denoising [64.11157141177208]
  We propose a spectral enhanced rectangle Transformer to model the spatial and spectral correlation in hyperspectral images. For the former, we exploit the rectangle self-attention horizontally and vertically to capture the non-local similarity in the spatial domain. For the latter, we design a spectral enhancement module that is capable of extracting global underlying low-rank property of spatial-spectral cubes to suppress noise.
  arXiv  Detail & Related papers  (2023-04-03T09:42:13Z)
• Coarse-to-Fine Sparse Transformer for Hyperspectral Image Reconstruction [138.04956118993934]
  We propose a novel Transformer-based method, coarse-to-fine sparse Transformer (CST) CST embedding HSI sparsity into deep learning for HSI reconstruction. In particular, CST uses our proposed spectra-aware screening mechanism (SASM) for coarse patch selecting. Then the selected patches are fed into our customized spectra-aggregation hashing multi-head self-attention (SAH-MSA) for fine pixel clustering and self-similarity capturing.
  arXiv  Detail & Related papers  (2022-03-09T16:17:47Z)
• Calibrated Hyperspectral Image Reconstruction via Graph-based Self-Tuning Network [40.71031760929464]
  Hyperspectral imaging (HSI) has attracted increasing research attention, especially for the ones based on a coded snapshot spectral imaging (CASSI) system. Existing deep HSI reconstruction models are generally trained on paired data to retrieve original signals upon 2D compressed measurements given by a particular optical hardware mask in CASSI. This mask-specific training style will lead to a hardware miscalibration issue, which sets up barriers to deploying deep HSI models among different hardware and noisy environments. We propose a novel Graph-based Self-Tuning ( GST) network to reason uncertainties adapting to varying spatial structures of masks among
  arXiv  Detail & Related papers  (2021-12-31T09:39:13Z)
• Hyperspectral Image Segmentation based on Graph Processing over Multilayer Networks [51.15952040322895]
  One important task of hyperspectral image (HSI) processing is the extraction of spectral-spatial features. We propose several approaches to HSI segmentation based on M-GSP feature extraction. Our experimental results demonstrate the strength of M-GSP in HSI processing and spectral-spatial information extraction.
  arXiv  Detail & Related papers  (2021-11-29T23:28:18Z)

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.