Deep Learning on Geometry Representations
Name
Smirnov_smirnov_PhD_EECS_2022_thesis.pdf
Description
Thesis PDF
Size
12.3 MB
Format
Adobe PDF
Checksum (MD5)
accc69190994297ac992dc5955fbb361
Author(s)
Smirnov, Dmitriy
Advisor(s)
Solomon, Justin
Date Issued
May 2022
Publisher
Massachusetts Institute of Technology
Abstract
While deep learning has been successfully applied to many tasks in computer graphics and vision, standard learning architectures often operate on shape representations that are dense and regular, like pixel or voxel grids. On the other hand, decades of computer graphics and geometry processing research have resulted in specialized algorithms and tools that use representations without such regular structure. In this thesis, we revisit conventional approaches in graphics in geometry to propose deep learning pipelines and inductive biases that are directly compatible with common geometry representations, without relying on simple uniform structure.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
In Copyright - Educational Use Permitted
Copyright MIT
Persistent DSpace Link
