Seminar on Human-Performance Capture

Abstract

Performance Capture refers to the technology and processes involved in digitally recreating the movements, poses, gestures, appearance, and expressions of a human and its surroundings. Methods to do so typically use body-worn sensors, RGB and depth cameras, and advanced Computer Vision algorithms to record the intricate details of a performer's movements.

Objective

The goal of the seminar is to familiarize students with exciting new research topics in this important area but also to teach basic scientific writing and oral presentation skills.

Content

Performance Capture refers to the technology and process involved in capturing and recreating the movements, gestures, and expressions of a human and its surroundings. It's a relevant field for various applications, including animation, virtual reality, and video games. It involves using advanced sensors, cameras, and computer vision algorithms to record the intricate details of a performer's movements, typically focusing on their face, body, clothing, and interactions. We will also explore the technology and applications behind high-end, multi-view capture stages, as the one ETH recently opened, Link Papers from scientific venues such as CVPR, ICCV, ECCV, and SIGGRAPH will be examined in-depth to explore the latest research in the field. Students present and discuss the papers to extract techniques and insights that can be applied to software & hardware projects. The seminar will have a different structure from regular seminars to encourage more discussion and a deeper learning experience. We will use a case-study format where all students read the same paper each week but fulfill different roles and hence prepare with different viewpoints in mind ( "presenter", "historian", "PhD", and “Journalist”). The final deliverables include: 20 Minute presentation as presenter 5 Minute presentation as historian 1 A4 research proposal as the PhD 1 A4 summary of the discussion as the Journalist. For each topic, a paper representing the state of the art of research or seminal work that inspired and fostered future work will be chosen.

Resources