CS 195

Week 6 Activity: Colloquium talk (on Zoom)

This week, Pomona College hosts a talk by James Tompkin, from Brown University. The talk begins at 4:15 PM on Thursday on Zoom.

For students enrolled in CS Colloquium (CS 195):

  • If you’re in Section 1, we expect you to attend the event when it occurs (synchronously).
  • If you’re in Section 2, we hope to record the event and post it for you to watch asynchronously.

Reconstructing the Real World with Neural Fields

Abstract

Over the past 30 years since the adoption of the digital camera, computer scientists have tried to reconstruct light and its interactions to create realistic digital representations of the real world. These are useful for measurement and remote communication, or even for interactive exploration to be a virtual tourist and see the world. Just in the past three years, our ability to do this has markedly increased in quality, generating significant hype around a set of methods using neural networks to optimize fields of physical properties, such as neural radiance fields (or NeRFs) - leading to fast adoption in industry and new startups. But, recent findings have shown that a more nuanced understanding is necessary to see through the hype and arrive at enlightenment. In this talk, I will attempt to provide a high-level view on what all this fuss is about - what the community has achieved, what's left to do, what core problems are difficult to overcome - while trying to show many beautiful results along the way.

About James Tompkin

James Tompkin is the John E. Savage Assistant Professor of Computer Science at Brown University. His research at the intersection of computer vision, computer graphics, and human-computer interaction helps develop new visual computing tools and experiences. His doctoral work at University College London on large-scale video processing and exploration techniques led to creative exhibition work in the Museum of the Moving Image in New York City. Postdoctoral work at Max-Planck-Institute for Informatics and Harvard University helped create new methods to edit content within images and videos. Recent research has developed new techniques for low-level depth reconstruction, view synthesis for VR, and content editing and generation.

When and How to Attend

  • Thursday, October 5
    • Location: Zoom link, Passcode: recursion. Please log in to see the Zoom link and passcode.
    • Talk runs from 4:15–5:30 PM

Recording for Section 2

(You must be logged in to view this video.)

This video is provided for students in Section 2 of CS 195 (and students in Section 1 who had to miss the talk due to extenuating circumstances). This is a private video, so please do not share it with others.

Required Assessment

To receive credit for attending this colloquium, complete the assessment:

Please do so at your soonest convenience, within 24 hours of seeing the talk.

(When logged in, completion status appears here.)