•   When: Wednesday, April 13, 2016 from 11:00 AM to 12:00 PM
•   Speakers: Yotam Gingold
•   Location: Nguyen Engineering, Room 4201
•   Export to iCal

Abstract

Curves, surfaces, and images lie at the core of computer graphics. Algorithms for image and shape editing are difficult, because the underlying structures---the flowers in a photograph or sharp edges in a shape---are obvious to humans but challenging for computers to recognize.

Painting in the physical world is a process that occurs over time. Later strokes cover earlier strokes, and strokes painted at a similar time are likely to be part of the same object. In the final painting, this temporal history is lost. Powerful layer-based or history-based image editing operations cannot be used. To enable these interactions, I will present a set of techniques to decompose a time lapse video of a painting into a sequence of translucent ``stroke'' images. I will present solutions for recovering physical (Kubelka and Munk) and digital (Porter and Duff) paint parameters from before/after image pairs. I will also present a pipeline for processing real-world videos of paintings capable of handling long-term occlusions, such as the painter's hand and its shadow, color shifts, and noise.

In the second portion of this talk, I will present a deformation technique that preserves the hand-made structure in 2D and 3D vector graphics (splines and subdivision surfaces). The technique is efficient, applies to the vector graphics formats used throughout 2D (PDF's, fonts, the web, illustrations) and 3D (industrial design and computer-aided design) computer graphics, and enables the entire body of existing linear blend skinning approaches to be used with vector graphics for the first time.

In the final portion of this talk, I will preview several types of crowd creativity (drawing, painting, singing, and sculpting).

Speaker's Bio

Yotam Gingold is an Assistant Professor in the computer science department at George Mason University. He runs the the Creativity and Graphics Lab (CraGL), whose mission is to solve challenging visual, geometry, and design problems and pursue foundational research into human creativity. His work is supported by the National Science Foundation (including a CAREER award) and Google. Previously he was a post-doctoral researcher in the computer science departments of Columbia University, Rutgers University, Tel-Aviv University, and Herzliya IDC. Yotam earned his Ph.D. in Computer Science from New York University in 2009, where he was awarded the Janet Fabri Prize for most outstanding dissertation.