THESIS DEFENSE: Deep Learning on Geometry Representations
, CSAIL MIT
Date: Thursday, April 21, 2022
Time: 10:00 AM to 11:00 AM Note: all times are in the Eastern Time Zone
Location: STAR Conference Room (32-D463)
Event Type: Thesis Defense
Host: Justin Solomon, CSAIL MIT
Contact: Mieke Moran, 617-253-5817, firstname.lastname@example.org
Speaker URL: None
TALK: THESIS DEFENSE: Deep Learning on Geometry Representations
Zoom Link: https://mit.zoom.us/j/91373670615?pwd=Z3FLejBwM0cvV2d3NTBQVGUzUUhjdz09
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 talk, I will show how revisiting conventional approaches can yield deep learning pipelines and inductive biases that are directly compatible with common geometry representations. In particular, I will discuss works on applying learning to triangle meshes, CAD-style parametric primitives, sprites, and hybrid explicit/implicit shapes with boundaries.
Dmitriy (Dima) Smirnov is a PhD student in the Geometric Data Processing group at MIT, advised by Professor Justin Solomon. His research lies on the intersection of computer graphics, geometry processing, and deep learning. Dima is an NSF Graduate Research Fellow and has done internships at Adobe Research and Pixar Research.
Thesis Committee: Justin Solomon (MIT), William T. Freeman (MIT), Mikhail Bessmeltsev (Université de Montréal)
Created by Mieke Moran at Tuesday, April 19, 2022 at 3:13 PM.