2026-09-19T09:28:05Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/1280892023-05-17T17:44:28Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023

Sertac Karaman. Lin, Muyuan(Scientist in mechanical engineering)Massachusetts Institute of Technology. Massachusetts Institute of Technology. Department of Mechanical Engineering. Massachusetts Institute of Technology. Department of Mechanical Engineering 2020-10-19T00:42:27Z 2020-10-19T00:42:27Z 2020 2020 https://hdl.handle.net/1721.1/128089 1200048688 Thesis: S.M., Massachusetts Institute of Technology, Department of Mechanical Engineering, 2020 Cataloged from PDF of thesis. Includes bibliographical references (pages 67-79). In this thesis, we investigated two important geometric vision problems, namely, depth estimation from a single RGB image, and 6-DoF object pose estimation from a partial point cloud. Geometric vision problems are concerned with extracting information (e.g. depth, agent trajectory, 3D structure, 6-DoF pose of objects) of the scene from noisy sensor data (e.g. RGB images, LiDAR) by exploiting geometric constraints (e.g. epipolar constraint, rigid motion of objects). Deep learning framework has achieved impressive progress in many computer vision tasks such as image recognition and segmentation. However, applying deep learning-based approaches to geometric vision problems, which are particularly important in safety-critical robotics applications, remains an open problem. The main challenge lies in the fact that it is not straightforward to incorporate geometric constraints, arising from image formation process and physical properties, to optimization problems. To this end, we explore possibilities of enforcing such constraints either by decomposing a problem into two sub-problems each respecting desired constraints, or designing an estimator establishing relationship between intermediate representations and predicted outputs. We propose a deep learning-based approach for -each problem. Through extensive experiments, we show that our proposed approaches produce results comparable with state of the art on public datasets. by Muyuan Lin. S.M. S.M. Massachusetts Institute of Technology, Department of Mechanical Engineering 79 pages eng Massachusetts Institute of Technology MIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided. http://dspace.mit.edu/handle/1721.1/7582 Mechanical Engineering. Deep learning-based approaches for depth and 6-DoF pose estimation Thesis application/pdf 2020-10-19T00:42:26Z Publication Master MechE unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="f1c940a5-6225-431b-ac6c-a2bf0adc61c7"> <Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type> <Language>eng</Language> <Title>Deep learning-based approaches for depth and 6-DoF pose estimation</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2020</PublicationDate> <Authors> <Author> <DisplayName>Lin, Muyuan(Scientist in mechanical engineering)Massachusetts Institute of Technology.</DisplayName> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> </Authors> <Editors> </Editors> <Publishers> <Publisher> <DisplayName>Massachusetts Institute of Technology</DisplayName> <OrgUnit /> </Publisher> </Publishers> <License>http://dspace.mit.edu/handle/1721.1/7582</License> <Keyword>Mechanical Engineering.</Keyword> <Abstract>In this thesis, we investigated two important geometric vision problems, namely, depth estimation from a single RGB image, and 6-DoF object pose estimation from a partial point cloud. Geometric vision problems are concerned with extracting information (e.g. depth, agent trajectory, 3D structure, 6-DoF pose of objects) of the scene from noisy sensor data (e.g. RGB images, LiDAR) by exploiting geometric constraints (e.g. epipolar constraint, rigid motion of objects). Deep learning framework has achieved impressive progress in many computer vision tasks such as image recognition and segmentation. However, applying deep learning-based approaches to geometric vision problems, which are particularly important in safety-critical robotics applications, remains an open problem. The main challenge lies in the fact that it is not straightforward to incorporate geometric constraints, arising from image formation process and physical properties, to optimization problems. To this end, we explore possibilities of enforcing such constraints either by decomposing a problem into two sub-problems each respecting desired constraints, or designing an estimator establishing relationship between intermediate representations and predicted outputs. We propose a deep learning-based approach for -each problem. Through extensive experiments, we show that our proposed approaches produce results comparable with state of the art on public datasets.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>