2026-09-18T17:20:06Zhttps://digital.library.adelaide.edu.au/server/oai/request

oai:digital.library.adelaide.edu.au:2440/1366922026-06-14T23:47:54Zcom_2440_14759col_2440_14760

Reid, Ian Shen, Chunhua (Zhejiang University) Bian, Jiawang School of Computer Science 2022 https://hdl.handle.net/2440/136692 Image-based depth estimation as a fundamental problem in computer vision allows for understanding the scene geometry using only cameras. This thesis addresses the specific problem of monocular depth estimation via self-supervised learning from RGB-only videos. Although existing work has shown partial excellent results in benchmark datasets, there remain several vital challenges that limit the use of these algorithms in general scenarios. To summarize, my identified challenges and contributions include: (i) Previous methods predict inconsistent depths over a video, which limits their uses in visual localization and mapping. To this end, I propose a geometry consistency loss that penalizes the multi-view depth misalignment in training, which enables scale-consistent depth estimation at inference time; (ii) Previous methods often diverge or show low-accuracy results when training on handheld camera captured videos. To address the challenge, I analyze the effect of camera motion on depth network gradients, and I propose an auto-rectify network to remove the relative rotation in training image pairs for robust learning; (iii) Previous methods fail to learn reasonable depths from highly dynamic scenes due to the non-rigidity. In this scenario, I propose a novel method, which constrains dynamic regions using an external well-trained depth estimation network and supervises static regions via multi-view losses. Comprehensive quantitative results and rich qualitative results are provided to demonstrate the advantages of the proposed methods over existing alternatives. The codes and pre-trained models have been released at https://github.com/JiawangBian Thesis (Ph.D.) -- University of Adelaide, School of Computer Science, 2022 en Monocular Depth Estimation, Self-supervised Learning, Visual SLAM Self-supervised Learning of Monocular Depth from Video Thesis This electronic version is made publicly available by the University of Adelaide in accordance with its open access policy for student theses. Copyright in this thesis remains with the author. This thesis may incorporate third party material which has been used by the author pursuant to Fair Dealing exceptions. If you are the owner of any included third party copyright material you wish to be removed from this electronic version, please complete the take down form located at: http://www.adelaide.edu.au/legalsopen.access