HSCNN+: Advanced CNN-Based Hyperspectral Recovery from RGB Images
By Zhan Shi, Chang Wen Chen, Zhiwei Xiong, Dong Liu, Feng Wu. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2018
307 citations recorded by the source corpus.
Hyperspectral recovery from a single RGB image has seen a great improvement with the development of deep convolutional neural networks (CNNs). In this paper, we propose two advanced CNNs for the hyperspectral reconstruction task, collectively called HSCNN+. We first develop a deep residual network named HSCNN-R, which comprises a number of residual blocks. The superior performance of this model comes from the modern architecture and optimization by removing the hand-crafted upsampling in HSCNN. Based on the promising results of HSCNN-R, we propose another distinct architecture that replaces the residual block by the dense block with a novel fusion scheme, leading to a new network named HSCNN-D. This model substantially deepens the network structure for a more accurate solution. Experimental results demonstrate that our proposed models significantly advance the state-of-the-art. In the NTIRE 2018 Spectral Reconstruction Challenge, our entries rank the 1st (HSCNN-D) and 2nd (HSCNN-R) places on both the "Clean" and "Real World" tracks. (Codes are available at [clean-r], [realworld-r], [clean-d], and [realworld-d].)
Subfields: Computer Vision and Pattern Recognition, Media Technology
View Paper: https://www.semanticscholar.org/paper/1921a5c407afdf06e058107b2fe8e416abd308ae
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Radu Timofte
- Yulun Zhang
- Ming-Hsuan Yang
- Chen Change Loy
- Lei Zhang
- Chao Dong
- Andrew Zisserman
In Media Technology
- Radu Timofte
- Luc Van Gool
- Yulun Zhang
- Chao Dong
- Hanspeter Pfister
- Kai Zhang
- Zudi Lin
- Alberto Signoroni
Citations in the corpus
- Deep Learning Meets Hyperspectral Image Analysis: A Multidisciplinary Review (2019, methodology): “Different DL solutions (CNN [36,37], 3D CNN [38], Dense and Residual Networks [39], Dirichlet networks [40], Generative Adversarial Networks [41]) have been proposed to improve the mapping and the spectral reconstruction by leveraging spatial context.”
- MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstruction (2022, methodology): “[67] use adapted residual blocks to build up a deep residual network HSCNN-R for SR.”