Office hours: Anupam: Tue 4-5 p.m. in GHC 7203, Jason: Thu 10–11 a.m. in GHC 7607, Goran: Wed 5–6 p.m. in GHC 7515 ...

Participants with some technical expertise who want to engage in an extensive hands-on group project in one of our three impact areas can join one of three hackathon experiences. Each hackathon will ...

Customization of text-to-image models enables users to insert custom concepts and generate the concepts in unseen settings. Existing methods either rely on costly test-time optimization or train ...

This paper develops a shape space framework for collision-aware geometric modeling, where basic geometric operations automatically avoid interpenetration. Shape spaces are a powerful tool for surface ...

Visual computing tasks such as 3D graphics and image processing are increasingly important to the capabilities and overall user experience delivered by computer systems ranging from high-end ...

Bundle adjustment jointly optimizes camera intrinsics and extrinsics and 3D point triangulation to reconstruct a static scene. The triangulation constraint, however, is invalid for moving points ...

Lecture time: Thursdays, 15:00-17:30 (15:00-16:10, break till 16:20, 16:20-17:30), GHC 4303.

Symbolic logic is fundamental to computer science, providing a foundation for the theory of programming languages, the theory of databases, AI, knowledge representation, automated reasoning, and ...

The advent of large-scale training has produced a cornucopia of powerful visual recognition models. However, generative models, such as GANs, have traditionally been trained from scratch in an ...

TL,DR: We propose a novel shape recovery approach that leverages the properties of heat transport, specifically heat conduction, induced on objects through a heating or cooling process. To demonstrate ...

The authors thank Saul Schleimer and Henry Segerman for helpful discussions about topological examples, and Nick Stadie for perspective on molecular symmetries. This work was supported by a Packard ...

We propose a 3D-aware conditional generative model for controllable photorealistic image synthesis. Given a 2D label map, such as a segmentation or edge map, our model synthesizes a photo from ...