AI Chat AI Image Generator AI Video Text to Speech

MXR-U-Nets for Real Time Hyperspectral Reconstruction

04/15/2020

∙

by Atmadeep Banerjee, et al.

∙

∙

In recent times, CNNs have made significant contributions to applications in image generation, super-resolution and style transfer. In this paper, we build upon the work of Howard and Gugger, He et al. and Misra, D. and propose a CNN architecture that accurately reconstructs hyperspectral images from their RGB counterparts. We also propose a much shallower version of our best model with a 10 video applications while still experiencing only about a 0.5 performance.

Atmadeep Banerjee
6 publications
Akash Palrecha
2 publications

page 4

page 5

research

∙ 04/12/2018

An efficient CNN for spectral reconstruction from RGB images

Recently, the example-based single image spectral reconstruction from RG...

0 Yigit Baran Can, et al. ∙

research

∙ 06/10/2018

Accurate Spectral Super-resolution from Single RGB Image Using Multi-scale CNN

Different from traditional hyperspectral super-resolution approaches tha...

0 Yiqi Yan, et al. ∙

research

∙ 10/22/2022

Efficient Hair Style Transfer with Generative Adversarial Networks

Despite the recent success of image generation and style transfer with G...

0 Muhammed Pektas, et al. ∙

research

∙ 02/01/2019

Deep Hyperspectral Prior: Denoising, Inpainting, Super-Resolution

Deep learning algorithms have demonstrated state-of-the-art performance ...

0 Oleksii Sidorov, et al. ∙

research

∙ 08/30/2021

The Application of Convolutional Neural Networks for Tomographic Reconstruction of Hyperspectral Images

A novel method, utilizing convolutional neural networks (CNNs), is propo...

4 Wei-Chih Huang, et al. ∙

research

∙ 04/05/2022

Real-time Hyperspectral Imaging in Hardware via Trained Metasurface Encoders

Hyperspectral imaging has attracted significant attention to identify sp...

12 Maksim Makarenko, et al. ∙

research

∙ 01/29/2018

Hyper-Hue and EMAP on Hyperspectral Images for Supervised Layer Decomposition of Old Master Drawings

Old master drawings were mostly created step by step in several layers u...

0 Amirabbas Davari, et al. ∙