News Archives

Learning models from visual data for 3D tracking, recognition, and animation

February 22, 2007

  • Date: Thursday, February 22, 2007 
  • Time: 11 am — 12:15 pm 
  • Place: ECE 118

Lorenzo Torresani  
Stanford University

Abstract: In this talk I will describe methods for the acquisition of computational models from visual data. In computer graphics, sophisticated models are necessary for simulation of real phenomena. In computer vision, visual models are used as a form of prior knowledge to disambiguate the otherwise ill-posed problem of image understanding. Traditionally, these models are manually constructed. My work proposes the application of machine learning algorithms that can automatically extract highly detailed models from visual observations.

I will begin with an algorithm for recovering non-rigid 3D models from image streams, without the use of training data or any prior knowledge about the modes of deformation of the object. I will describe how this method can be used to reconstruct subtle human body deformations in 3D space from single-view video under severe cases of occlusion and variable illumination.

I will then present a technique for learning classification features from high-dimensional data, such as images consisting of thousands of pixels. When applied to a set of face images with identity labels, this algorithm automatically extracts the features that are most salient for the purpose of identification and discards visual effects unimportant for recognition, such as non-uniform illumination and facial expressions.

I will conclude by describing a system for motion style editing based on a style model learned from human perceptual observations and motion capture data. This system enables users to create novel versions of pre-recorded motion sequences in desired styles.

Bio Lorenzo Torresani is a Senior Researcher at Riya, Inc. He received a Laurea Degree in Computer Science with summa cum laude honors from the University of Milan (Italy) in 1996, and an M.S. and a Ph.D. in Computer Science from Stanford University in 2001 and 2005, respectively. His previous professional experience includes working as a researcher at the Courant Institute of New York University, and at Digital Persona, Inc. His research interests are in computer vision, computer animation, and machine learning. He received the Best Student Paper Award at the IEEE Conference On Computer Vision and Pattern Recognition, 2001, for his work on visual tracking and 3D reconstruction of non-rigid objects.