///Learning to Align without Geometric Supervision
Loading Events
This event has passed.

PhD Speaking Qualifier

April

3
Wed
Chen-Hsuan Lin PhD Student Robotics Institute,
Carnegie Mellon University
Wednesday, April 3
2:00 pm
- 3:00 pm
GHC 4405
Learning to Align without Geometric Supervision

Abstract:
Extracting geometric information from image data is a highly nonlinear problem that exhibits in a number of visual recognition tasks such as object localization, facial landmark tracking and human pose estimation. Successful alignment across image data often serves as a crucial component in making them possible. In this talk, I will present how one can achieve alignment for deep learning without the need of explicit geometric supervision. I will present three of my recent/previous works in this line: (1) resolving large spatial variations within image data for efficient visual learning, (2) correcting the geometry of images to create realistic composites, and (3) reconstructing 3D object meshes from RGB videos posed as a piecewise 2D image alignment problem, which can be achieved without any mask or depth information.

Research Qualifier Committee:
Simon Lucey, Advisor
Martial Hebert
Deva Ramanan
Chen Kong