Proceedings ArticleDOI
2D-3D CNN Based Architectures for Spectral Reconstruction from RGB Images
Sriharsha Koundinya,Himanshu Sharma,Manoj Sharma,Avinash Upadhyay,Raunak Manekar,Rudrabha Mukhopadhyay,Abhijit Karmakar,Santanu Chaudhury +7 more
- pp 844-851
Reads0
Chats0
TLDR
This work proposes a 2D convolution neural network and a 3D convolved neural network based approaches for hyperspectral image reconstruction from RGB images that achieves very good performance in terms of MRAE and RMSE.Abstract:
Hyperspectral cameras are used to preserve fine spectral details of scenes that are not captured by traditional RGB cameras that comprehensively quantizes radiance in RGB images. Spectral details provide additional information that improves the performance of numerous image based analytic applications, but due to high hyperspectral hardware cost and associated physical constraints, hyperspectral images are not easily available for further processing. Motivated by the performance of deep learning for various computer vision applications, we propose a 2D convolution neural network and a 3D convolution neural network based approaches for hyperspectral image reconstruction from RGB images. A 2D-CNN model primarily focuses on extracting spectral data by considering only spatial correlation of the channels in the image, while in 3D-CNN model the inter-channel co-relation is also exploited to refine the extraction of spectral data. Our 3D-CNN based architecture achieves very good performance in terms of MRAE and RMSE. In contrast to 3D-CNN, our 2D-CNN based architecture also achieves comparable performance with very less computational complexity.read more
Citations
More filters
Proceedings ArticleDOI
lambda-Net: Reconstruct Hyperspectral Images From a Snapshot Measurement
TL;DR: The λ-net, which reconstructs hyperspectral images from a single shot measurement, can finish the reconstruction task within sub-seconds instead of hours taken by the most recently proposed DeSCI algorithm, thus speeding up the reconstruction >1000 times.
Proceedings ArticleDOI
NTIRE 2018 Challenge on Spectral Reconstruction from RGB Images
TL;DR: This paper reviews the first challenge on spectral image reconstruction from RGB images, i.e., the recovery of whole-scene hyperspectral (HS) information from a 3-channel RGB image.
Book ChapterDOI
End-to-End Low Cost Compressive Spectral Imaging with Spatial-Spectral Self-Attention
Ziyi Meng,Jiawei Ma,Xin Yuan +2 more
TL;DR: This work reproduces a stable single disperser CASSI system and proposes a novel deep convolutional network to carry out the real-time reconstruction by using self-attention, employing Spatial-Spectral Self-Attention (TSA) to process each dimension sequentially, yet in an order-independent manner.
Proceedings ArticleDOI
Adaptive Weighted Attention Network With Camera Spectral Sensitivity Prior for Spectral Reconstruction From RGB Images
TL;DR: Zhang et al. as mentioned in this paper proposed an adaptive weighted channel attention (AWCA) module to reallocate channel-wise feature responses via integrating correlations between channels, and a patch-level second-order non-local (PSNL) module is developed to capture long-range spatial contextual information.
Proceedings ArticleDOI
Hierarchical Regression Network for Spectral Reconstruction from RGB Images
TL;DR: A 4-level Hierarchical Regression Network (HRNet) with PixelShuffle layer as inter-level interaction with a residual dense block to remove artifacts of real world RGB images and a residual global block to build attention mechanism for enlarging perceptive field is proposed.
References
More filters
Journal ArticleDOI
Automatic ink mismatch detection for forensic document analysis
TL;DR: A novel joint sparse band selection technique that selects informative bands from hyperspectral images for accurate ink mismatch detection is proposed and extensive experiments show that the proposed band selection method improves average accuracy up to 15%, compared to using all bands.
Proceedings ArticleDOI
Hyperspectral imaging of bruised skin
TL;DR: In this article, a hyperspectral imaging system was used to measure the temporal development of bruised skin in a human volunteer, where the bruises were inflicted by paintball bullets and the spectral sampling intervals were 3.7 and 5 nm, respectively.
Proceedings ArticleDOI
Multispectral imaging with a liquid crystal tunable filter
Peter J. Miller,Clifford C. Hoyt +1 more
TL;DR: The tunable liquid crystal filter (LCTF) as discussed by the authors is an optical filter, similar to an interference filter, whose center wavelength is electronically tunable with no moving parts, in a few milliseconds, across hundreds of nanometers.
Proceedings ArticleDOI
Spatio-spectral reconstruction of the multispectral datacube using sparse recovery
TL;DR: New computational methods that estimate the datacube from measurements with a conventional digital camera are presented, that jointly recovers the spatio-spectral datacubes by exploiting the data sparsity in a transform representation.
Proceedings ArticleDOI
Adversarial Networks for Spatial Context-Aware Spectral Image Reconstruction from RGB
TL;DR: In this article, a conditional generative adversarial framework is used to capture spatial semantics for hyperspectral image reconstruction, achieving a Root Mean Squared Error (RMSE) drop of 44.7% and a Relative RMSE drop of 47.0%.