Computer Science Speaker Series Master Calendar

View Full Calendar

Vision Seminar: Shubham Tulsiani, "3D from one or more Images"

Event Type
Svetlana Lazebnik
wifi event
Feb 1, 2022   10:00 am  
Originating Calendar
Computer Science Speakers Calendar


Meeting ID: 862 3823 3298

Password: 684009


Title: 3D from one or more Images


Abstract: The world we live in is incredibly diverse, comprising of over 10k natural and man-made object categories. To allow scalable 3D prediction for such generic objects, recent approaches have striven to learn 3D from category-level segmented image collections. However, these methods learn independent category-specific models from scratch, often relying on adversarial or template-based priors to regularize learning. In this talk, I will present a simpler alternative for scalable 3D reconstruction — learning a unified model across 150 categories while using synthetic 3D data on some categories to help regularize learning for others. Moving beyond single-view reconstruction, I will also show how sparse multi-view collections can allow us to infer fine instance-level 3D shapes for generic objects using as few as 8 images.


Bio: Shubham Tulsiani is an Assistant Professor in the Robotics Institute at CMU. Prior to this, he was research scientist at Facebook AI Research (FAIR) and received a PhD. in Computer Science from UC Berkeley in 2018. He is interested in building perception systems that can infer the spatial and physical structure of the world they observe.

link for robots only