Better depth and motion from thermal images by improving self-supervised learning
Better depth and motion from thermal images by improving self-supervised learning
Maximizing Self-supervision from Thermal Image for Effective Self-supervised Learning of Depth and Ego-motion
arXiv paper abstract https://arxiv.org/abs/2201.04387v1
arXiv PDF paper https://arxiv.org/pdf/2201.04387v1.pdf
… self-supervised learning of depth and ego-motion from thermal images shows strong robustness and reliability under challenging scenarios.
However … thermal image properties such as weak contrast, blurry edges, and noise hinder to generate effective self-supervision
… Therefore, most research relies on additional self-supervision sources such as well-lit RGB images, generative models, and Lidar information.
… conduct an in-depth analysis of thermal image characteristics that degenerates self-supervision from thermal images.
… propose … thermal image mapping method that significantly increases image information, such as overall structure, contrast, and details, while preserving temporal consistency.
… shows outperformed depth and pose results than previous state-of-the-art networks without leveraging additional RGB guidance.
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
