Past Meetup

Automatic Photo Retouching and Tools for Computer Animation Simulation

This Meetup is past

21 people went

Location image of event venue

Details

Welcome to the first event of Boston Computational Creativity group!

Agenda:

6:00 - 6:30 Networking and Pizza

6:30 - 7:15 First speaker: Yuanming Hu

He will introduce two computational tools to help artist better create.

The first tool is for photo retouching. Retouching can significantly elevate the visual appeal of photos, but many casual photographers lack the expertise to do this well. To address this issue, He will introduce a deep learning approach that can automatically retouch photos. In contrast to many deep learning systems, theirs provides users with an understandable solution in the form of conventional retouching edits, rather than just a “black-box” result.
Detail: https://arxiv.org/pdf/1709.09602.pdf

The second tool is for computer simulation and animation, which is ubiquitous nowadays in film, games and even scientific research. As a novel physical simulation system, this tool enables simulation of cutting materials (e.g. banana, cheese, jelly) and mutual interactions between deformable and rigid bodies. Their approach makes it easy for artists to create realistic and stunning computer animation for visual effects. In addition, it also enables scientists to virtually test new robots without manufacturing them, which can speed up robot design.
Detail: https://www.youtube.com/watch?v=8iyvhGF9f7o&feature=youtu.be

Bio: Yuanming Hu is a first-year Ph.D. student at MIT CSAIL. His research is in computer graphics, especially physically based simulation and computational photography. He is the creator and main developer of Taichi, an open source computer graphics library.

7:15 - 8:00 Second speaker: Tomer Weiss

Simulating the movement of a large number of people is important in many situations, such as the evacuation of a building in an emergency, urban planning, and visual effects. In this talk, he will introduce his recent work in crowd simulation for 100K+ agents, which was previously unachievable. This new method is suitable for use in interactive games, and was recently presented in the ACM SIGGRAPH conference on Motion in Games 2017, where it received the best paper award.
Detail: https://www.youtube.com/watch?v=NltNl7_1uHs

Bio: Tomer Weiss defended his PhD thesis at the University of California Los Angeles earlier this year. His research interests include computer graphics and optimization methods. Recently, he joined Wayfair in Boston, and is now contributing to the Operations Research team, focusing on modeling and engineering.

8:00 on: More networking.