Generative Adversarial Networks for Spectral Super-Resolution and Bidirectional RGB-To-Multispectral Mapping

Lore, Kin Gwn; Reddy, K. Ashoka; Giering, Michael; Bernal, Edgar A.

doi:10.1109/cvprw.2019.00122

Cited by 16 publications

(15 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We find that the reconstructed RGB images and ground truth images are too close to judge with the naked eyes. Furthermore, the reconstruction behaves better than Kin et al's work [16].…”

Section: ) the Qualitative Evaluationmentioning

confidence: 63%

“…Furthermore, at the 2019 CVPR workshop, Kin et al demonstrated a way of directly reconstructing MSIs from RGBs by using conditional GAN. Since their method is purely data-driven, it could easily lead to hallucinatory results [16].…”

Section: Related Workmentioning

confidence: 99%

“…In this subsection, the qualitative results of the two phases: RGB to MSI and MSI to RGB, are shown. Since we chose Kin et al's work [16] as the baseline, all the selected images and training configurations are the same as theirs. Figure 5 shows the result of the RGB to the MSI.…”

Section: ) the Qualitative Evaluationmentioning

confidence: 99%

“…Furthermore, the reconstruction experiment is bi-directional, which means that we measure the results of converting both the RGB to the MSI and the MSI to the RGB. In order to highlight the comparison easily, we include our results with Berk et al's [14], Kin et al's [16], and Arad et al's [10] in the Table 3 and Table 4, respectively.…”

Section: ) the Quantitative Measurementmentioning

confidence: 99%

“…We choose a more challenging dataset split ratio, 50%:50%. Only a few works, like Kin et al's [16], have chosen this kind of split ratio to the best of our knowledge. Moreover, the approach of Kin et al also contains a GAN loss like ours.…”

Section: B the Cave Dataset 1) The Dataset Introduction And The Hypementioning

confidence: 99%

See 4 more Smart Citations

Multispectral Image Reconstruction From Color Images Using Enhanced Variational Autoencoder and Generative Adversarial Network

et al. 2021

View full text Add to dashboard Cite

“…We find that the reconstructed RGB images and ground truth images are too close to judge with the naked eyes. Furthermore, the reconstruction behaves better than Kin et al's work [16].…”

Section: ) the Qualitative Evaluationmentioning

confidence: 63%

Section: Related Workmentioning

confidence: 99%

Section: ) the Qualitative Evaluationmentioning

confidence: 99%

Section: ) the Quantitative Measurementmentioning

confidence: 99%

Section: B the Cave Dataset 1) The Dataset Introduction And The Hypementioning

confidence: 99%

See 3 more Smart Citations

Multispectral Image Reconstruction From Color Images Using Enhanced Variational Autoencoder and Generative Adversarial Network

et al. 2021

View full text Add to dashboard Cite

Grasp pose detection for deformable daily items by pix2stiffness estimation

et al. 2022

View full text Add to dashboard Cite

SPIDE-Net: Spectral Prior-Based Image Dehazing and Enhancement Network

Qasim

Raja

2022

IEEE Access

View full text Add to dashboard Cite

During hazy or foggy conditions, the acquired images are degraded and resulting in reduced visibility, contrast and color fidelity. This image degradation occurs due to atmospheric particles that attenuates and scatters the source radiations. The degradation intensity depends on diverse scenarios having variable densities of atmospheric particles, their wavelength and distance from acquisition device. Existing image dehazing methods for visible-band images are either based on prior assumptions to reconstruct the transmission map or used some learning mechanism to directly estimate the dehazed image. Recently, performance comparison of existing popular image dehazing methods using spectral hazy images are performed in which selected wavelength bands from different fog density levels are used for comparisons. The comparison results showed performance degradation of existing methods with wavelength bands selection and fog density levels. In this study, we design an effective spectral and prior based image dehazing and enhancement network (SPIDE-Net) showing better performance as compared to existing methods when using spectral hazy images from variable wavelength bands and fog density levels. Our SPIDE-Net consists of two networks:1) Spectral Image Dehazing Network (SID-Net), which is trained on multi-spectral hazy images between 450 nm and 720 nm, and takes advantage of varying attenuations in different wavelength bands. 2) Multi-scale Prior based image Dehazing Network (MPD-Net) uses multi-scale dark-channel and color attenuation priors on image triplets selected from a multi-spectral hazy image database. The proposed method is an encoder-decoder style CNN network that combines information from both SID-Net and MPD-Net by sharing a common decoder stage. The proposed network was trained on the SHIA dataset and evaluated at different fog density levels. Compared with popular prior and learning-based methods evaluated at SHIA dataset, the proposed method achieves superior performance both qualitatively and quantitatively.INDEX TERMS Single image dehazing, haze relevant feature, multi-scale, dark channel prior, color attenuation prior, deep convolutional neural network, multi-spectral image dehazing.

show abstract

Generative Adversarial Networks for Spectral Super-Resolution and Bidirectional RGB-To-Multispectral Mapping

Cited by 16 publications

References 21 publications

Multispectral Image Reconstruction From Color Images Using Enhanced Variational Autoencoder and Generative Adversarial Network

Multispectral Image Reconstruction From Color Images Using Enhanced Variational Autoencoder and Generative Adversarial Network

Grasp pose detection for deformable daily items by pix2stiffness estimation

SPIDE-Net: Spectral Prior-Based Image Dehazing and Enhancement Network

Contact Info

Product

Resources

About