- Library Home /
- Search Collections /
- Open Collections /
- Browse Collections /
- UBC Theses and Dissertations /
- Modularizing deep learning for geometry-aware registration...
Open Collections
UBC Theses and Dissertations
UBC Theses and Dissertations
Modularizing deep learning for geometry-aware registration and reconstruction Jiang, Wei
Abstract
In this work, we explore the modularization of deep learning for geometry-aware registration and reconstruction, with a particular focus on cameras registration and human reconstruction from videos. The traditional methods for these tasks have been challenged by deep learning approaches, but end-to-end learning can be limited in terms of generalization, transparency, and controllability. Modularization breaks the task into smaller subtasks and allows each to be addressed individually using traditional methods or deep learning techniques. Through modularization, we are able to embed knowledge from the real world, enabling better generalization, simpler and more effective learning, explainable and transparent models, and geometry-awareness. Specifically, this work consists of four major chapters, each presenting a modularized approach to solve a specific geometric problem. Firstly, a novel linearized multi-sampling method is proposed to enable better image alignment and learning. Secondly, the homography warping is modularized out of the pipeline allowing optimization through the learned error for accurate sports field registration. Thirdly, by modularizing the robust estimation and 3D map from the pose estimation pipeline, the neural network can focus on learning accurate image correspondences. Finally, the modularization of human scene positioning and mesh skinning allows for the reconstruction of animatable human avatar from video. Overall, our work demonstrates the power of modularization, and we hope it will inspire future research on modularization and its potential applications to other areas.
Item Metadata
Title |
Modularizing deep learning for geometry-aware registration and reconstruction
|
Creator | |
Supervisor | |
Publisher |
University of British Columbia
|
Date Issued |
2023
|
Description |
In this work, we explore the modularization of deep learning for geometry-aware registration and reconstruction, with a particular focus on cameras registration and human reconstruction from videos. The traditional methods for these tasks have been challenged by deep learning approaches, but end-to-end learning can be limited in terms of generalization, transparency, and controllability.
Modularization breaks the task into smaller subtasks and allows each to be addressed individually using traditional methods or deep learning techniques. Through modularization, we are able to embed knowledge from the real world, enabling better generalization, simpler and more effective learning, explainable and transparent models, and geometry-awareness.
Specifically, this work consists of four major chapters, each presenting a modularized approach to solve a specific geometric problem. Firstly, a novel linearized multi-sampling method is proposed to enable better image alignment and learning. Secondly, the homography warping is modularized out of the pipeline allowing optimization through the learned error for accurate sports field registration. Thirdly, by modularizing the robust estimation and 3D map from the pose estimation pipeline, the neural network can focus on learning accurate image correspondences. Finally, the modularization of human scene positioning and mesh skinning allows for the reconstruction of animatable human avatar from video.
Overall, our work demonstrates the power of modularization, and we hope it will inspire future research on modularization and its potential applications to other areas.
|
Genre | |
Type | |
Language |
eng
|
Date Available |
2023-03-07
|
Provider |
Vancouver : University of British Columbia Library
|
Rights |
Attribution-NonCommercial-NoDerivatives 4.0 International
|
DOI |
10.14288/1.0427395
|
URI | |
Degree | |
Program | |
Affiliation | |
Degree Grantor |
University of British Columbia
|
Graduation Date |
2023-05
|
Campus | |
Scholarly Level |
Graduate
|
Rights URI | |
Aggregated Source Repository |
DSpace
|
Item Media
Item Citations and Data
Rights
Attribution-NonCommercial-NoDerivatives 4.0 International