HomeProjectsPublicationsPeopleLinks

Nonrigid Structure From Motion in Trajectory Space
Ijaz Akhter, Yaser Sheikh, Sohaib Khan, Takeo Kanade, NIPS 2008

Downloads
NIPS '08 paper
Spotlight Slide [PDF Slide] [MP3 Audio]
Code and Datasets used in the paper

Abstract
Existing approaches to nonrigid structure from motion assume that the instantaneous 3D shape of a deforming object is a linear combination of shape basis, which have to be estimated anew for each video sequence. In contrast, we propose that the evolving 3D structure be described by a linear ombination of basis trajectories. The principal advantage of this approach is that we do not need to estimate any basis vectors during computation. We show that generic bases over trajectories, such as the Discrete Cosine Transform (DCT) basis, can be used to compactly describe most real motions. This results in a significant reduction in unknowns, and corresponding stability in estimation. We report empirical performance, quantitatively using motion capture data, and qualitatively on several video sequences exhibiting nonrigid motions including piece-wise rigid motion, partially nonrigid motion (such as a facial expression), and highly nonrigid motion (such as a person dancing)

Video Results

Nonrigid Structure from Motion from Ijaz Akhter on Vimeo.

Datasets used in the paper
This readme.txt file explains the structure of data files

Mocap Datasets for Quantitative Evalution [from http://mocap.cs.cmu.edu]

Drink Dataset:

[.mat file] [video of results]

Matrix Sequence: