From Video to Virtual: Object-centric 3D scene understanding from videos
IEEE CS SD Invited Seminar Series 2025 - Lecture 3 (Virtual)
The growing demand for immersive, interactive experiences has underscored the importance of 3D data in understanding our surroundings. Traditional methods for capturing 3D data are often complex and equipment-intensive. In contrast, my research aims to utilize unconstrained videos, such as those from augmented reality glasses, to effortlessly capture scenes and objects in their full 3D complexity. As a first step, I will describe a method to incorporate Epipolar Geometry priors in multi-view Transformer models to enable identifying objects across extreme pose variations. Next, I will discuss my work "Contrastive Lift" on 3D object segmentation using 2D pre-trained foundation models, following which I will talk about addressing the same problem using language.
Date and Time
Location
Hosts
Registration
- Date: 25 Feb 2025
- Time: 03:00 PM to 04:00 PM
- All times are (UTC-08:00) Pacific Time (US & Canada)
-
Add Event to Calendar
- Starts 12 February 2025 12:00 AM
- Ends 25 February 2025 12:00 AM
- All times are (UTC-08:00) Pacific Time (US & Canada)
- No Admission Charge
Speakers
Yash Bhalgat of University of Oxford's Visual Geometry Group (VGG)
From Video to Virtual: Object-centric 3D scene understanding from videos
Biography:
Yash Bhalgat is a final year PhD student at University of Oxford's Visual Geometry Group (VGG) supervised by Andrew Zisserman, Andrea Vedaldi, Joao Henriques and Iro Laina. His research is broadly in 3D Computer Vision and Machine Learning, with focus on geometry-aware transformers, neural rendering, vision-language models. Previously, he was a Senior Researcher at Qualcomm AI Research in San Diego working on efficient deep learning. He received his Masters in CS from University of Michigan - Ann Arbor, and his Bachelors in EE from IIT Bombay.
Agenda
- Invited talk from Yash Bhalgat the final year PhD student at University of Oxford's Visual Geometry Group (VGG) supervised by Andrew Zisserman, Andrea Vedaldi, Joao Henriques and Iro Laina.
- Q/A Session
- 3rd lecture of the 2025 Invited Seminar Series (Virtual) organized by IEEE Computer Society San Diego Chapter. Previous lectures: 2023 and 2024 invited seminar series.