As part of our at our SFU VINCI Visual Computing and Robotics (VCR) Seminar series, we are excited to have Dr. Vladimir (Vova) Kim from Adobe Research.

Vova Kim

Date: Friday, Feb 14th, 2024

Time: 12:00 PM - 1:30 PM PST

Location: TASC 1 9204, Burnaby campus

Talk Title: Controllable 3D Generation

Abstract: State-of-the-art generative models enable users to create complex 3D shapes from sparse and partial inputs, such as text or images. These methods, however, still lack wide adoption in the professional artist community due to a lack of precise and rich controls enabled by traditional tools. In this talk I will describe several methods that aim to complement traditional workflows by providing AI-assisted tools to perform tasks that are commonly done by artists, such as iterative sculpting, deformation, detailization and refinement, and material painting. Our techniques especially focus on traditional representations (such as meshes and material maps) to ensure that they can be easily integrated in existing pipelines.

Biography: Dr. Vladimir (Vova) Kim is a Senior Research Scientist at Adobe Research. He works at the intersection of computer graphics, computer vision, and machine learning, developing techniques that enable novel interfaces for creative tasks. His recent focus is on novel neural representations for geometric data with applications to interactive 3D modeling, geometry analysis, geometry processing, and other content creation workflows. He was a postdoctoral scholar at Stanford University (2013-2015), received his PhD in the Computer Science Department at Princeton University (2008-2013), and his BA in Mathematics and Computer Science at Simon Fraser University (2003-2008). He has been a member of the International Program Committee for SIGGRAPH (2015, 2020, 2023), SIGGRAPH Asia (2022), Symposium on Geometry processing, Eurographics, and regularly reviews for graphics and vision venues, such as Transaction on Graphics, CVPR, ICCV, ECCV, and NeurIPS.