Monocular Depth Estimation using Adversarial Training
2020-07
Loading...
View/Download File
Persistent link to this item
Statistics
View StatisticsJournal Title
Journal ISSN
Volume Title
Title
Monocular Depth Estimation using Adversarial Training
Authors
Published Date
2020-07
Publisher
Type
Thesis or Dissertation
Abstract
Monocular depth estimation is a fundamentally challenging problem in Computer Vision. It is useful for Robotics applications where design constraints prohibit the use of multiple cameras. It also finds widespread use in autonomous driving. Since the task is to estimate depth from a single image, rather than two or more, a global perspective of the scene is required. Pixel-wise losses like reconstruction loss, left-right consistency loss, capture local scene information. However, they do not take into account global scene consistency. Generative Adversarial Networks(GANs) effectively capture the global structure of the scene and produce real-looking images, so they have the potential of depth estimation from a single image. This work focuses on using adversarial training for a supervised monocular depth estimation task in combination with pixel-wise losses. We observe that with minimal depth-supervised training, there is a significant reduction of error in depth estimation in a number of GAN variants explored.
Description
University of Minnesota M.S. thesis. 2020. Major: Computer Science. Advisor: Junaed Sattar. 1 computer file (PDF); 72 pages.
Related to
Replaces
License
Series/Report Number
Funding information
Isbn identifier
Doi identifier
Previously Published Citation
Other identifiers
Suggested citation
Mitra, Pallavi. (2020). Monocular Depth Estimation using Adversarial Training. Retrieved from the University Digital Conservancy, https://hdl.handle.net/11299/216319.
Content distributed via the University Digital Conservancy may be subject to additional license and use restrictions applied by the depositor. By using these files, users agree to the Terms of Use. Materials in the UDC may contain content that is disturbing and/or harmful. For more information, please see our statement on harmful content in digital repositories.