Learning to Enhance Visual Quality via Hyperspectral Domain Mapping (Student Abstract)

Harsh Sinha, Aditya Mehta, Murari Mandal, Pratik Narang

AAAI 2021 pp. 15895-15896

doi:10.1609/AAAI.V35I18.17944 /aaai/2021/sinha2021aaai-learning/

Abstract

Deep learning based methods have achieved remarkable success in image restoration and enhancement, but a majority of such methods rely on RGB input images. These methods fail to take into account the rich spectral distribution of natural images. We propose a deep architecture, SpecNet which computes spectral profile to estimate pixel-wise dynamic range adjustment of a given image. First, we employ an unpaired cycle-consistent framework to generate hyperspectral images (HSI) from low-light input images. HSI are further used to generate a normal light image of the same scene. In order to infer a plausible HSI from a RGB image we incorporate a self-supervision and a spectral profile regularization network. We evaluate the benefits of optimizing the spectral profile for real and fake images in low-light conditions on the LOL Dataset.

PDF AAAI Semantic Scholar

Cite

Text

Sinha et al. "Learning to Enhance Visual Quality via Hyperspectral Domain Mapping (Student Abstract)." AAAI Conference on Artificial Intelligence, 2021. doi:10.1609/AAAI.V35I18.17944

Markdown

[Sinha et al. "Learning to Enhance Visual Quality via Hyperspectral Domain Mapping (Student Abstract)." AAAI Conference on Artificial Intelligence, 2021.](https://mlanthology.org/aaai/2021/sinha2021aaai-learning/) doi:10.1609/AAAI.V35I18.17944

BibTeX

@inproceedings{sinha2021aaai-learning,
  title     = {{Learning to Enhance Visual Quality via Hyperspectral Domain Mapping (Student Abstract)}},
  author    = {Sinha, Harsh and Mehta, Aditya and Mandal, Murari and Narang, Pratik},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2021},
  pages     = {15895-15896},
  doi       = {10.1609/AAAI.V35I18.17944},
  url       = {https://mlanthology.org/aaai/2021/sinha2021aaai-learning/}
}