3D Deep Learning for Object-Centric Geometric Perception

Object-centric geometric perception aims at extracting the geometric attributes of 3D objects. These attributes include shape, pose, and motion of the target objects, which enable fine-grained object-level understanding for various tasks in graphics, computer vision, and robotics. With the growth of 3D geometry data and 3D deep learning methods, it becomes more and more likely to achieve such tasks directly using 3D input data. Among different 3D representations, a 3D point cloud is a simple, common, and memory-efficient representation that could be directly retrieved from multi-view images, depth scans, or LiDAR range images. Different challenges exist in achieving object-centric geometric perception, such as achieving a fine-grained geometric understanding of common articulated objects with multiple rigid parts, learning disentangled shape and pose representations with fewer labels, or tackling dynamic and sequential geometric input in an end-to-end fashion. Here we identify and solve these challenges from a 3D deep learning perspective by designing effective and generalizable 3D representations, architectures, and pipelines. We propose the first deep pose estimation for common articulated objects by designing a novel hierarchical invariant representation. To push the boundary of 6D pose estimation for common rigid objects, a simple yet effective self-supervised framework is designed to handle unlabeled partial segmented scans. We further contribute a novel 4D convolutional neural network called PointMotionNet to learn spatio-temporal features for 3D point cloud sequences. All these works advance the domain of object-centric geometric perception from a unique 3D deep learning perspective.

Name thesis:degree_name

Doctor of Philosophy

Level thesis:degree_level

doctoral

Discipline thesis:degree_discipline

Computer Engineering

Department dc:contributor.department

Electrical and Computer Engineering

Grantor dc:publisher

Virginia Tech

Year dc:date.issued

2022

Author dc:creator

• Li, Xiaolong

Chair dc:contributor.committeechair

• Abbott, A. Lynn

Committee members dc:contributor.committeemember

• Huang, Jia-Bin
• Zhou, Wei
• Polys, Nicholas F.
• Williams, Ryan K.

• point cloud
• pose estimation
• equivariance
• motion forecasting
• shape completion

Statement dc:rights

• Creative Commons Attribution-NonCommercial 4.0 International

Licence dc:rights.uri

• http://creativecommons.org/licenses/by-nc/4.0/

Language dc:language.iso

en

Dc Identifier Other

vt_gsexam:35016

OAI identifier oai:identifier

oai:vtechworks.lib.vt.edu:10919/111077