Computational Visual Morphology and Simple Visual Sensing
Event details
| Date | 30.08.2024 |
| Hour | 11:30 › 13:30 |
| Speaker | Rishubh Singh |
| Location | |
| Category | Conferences - Seminars |
EDIC candidacy exam
Exam president: Prof.Martin Schrimpf
Thesis advisor: Prof. Amir Zamir
Co-examiner: Prof. Jamie Paik
Abstract
A de facto standard in solving computer vision problems is to use a common high-resolution camera and choose its placement on an agent (i.e., position and orientation) based on human intuition. On the other hand, extremely simple and well-designed visual sensors found throughout nature allow many organisms to perform diverse, complex behaviors. With inspiration from this, I want to explore how effective simple visual sensors are in solving vision tasks and if simple visual sensing can provide solutions to tasks such as touch that are not usually associated with vision based perception.
Background papers
Eye evolution and its functional basis, https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3632888/
Transform2Act: Learning a Transform-and-Control Policy for Efficient Agent Design, https://arxiv.org/abs/2110.03659
SPIN: Simultaneous Perception, Interaction and Navigation, https://arxiv.org/abs/2405.07991
Exam president: Prof.Martin Schrimpf
Thesis advisor: Prof. Amir Zamir
Co-examiner: Prof. Jamie Paik
Abstract
A de facto standard in solving computer vision problems is to use a common high-resolution camera and choose its placement on an agent (i.e., position and orientation) based on human intuition. On the other hand, extremely simple and well-designed visual sensors found throughout nature allow many organisms to perform diverse, complex behaviors. With inspiration from this, I want to explore how effective simple visual sensors are in solving vision tasks and if simple visual sensing can provide solutions to tasks such as touch that are not usually associated with vision based perception.
Background papers
Eye evolution and its functional basis, https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3632888/
Transform2Act: Learning a Transform-and-Control Policy for Efficient Agent Design, https://arxiv.org/abs/2110.03659
SPIN: Simultaneous Perception, Interaction and Navigation, https://arxiv.org/abs/2405.07991
Practical information
- General public
- Free
Contact
- edic@epfl.ch