Qualitative Structure From Motion

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


Exact structure from motion is an ill-posed computation and therefore very sensitive to noise. In this work I describe how a qualitative shape representation, based on the sign of the Gaussian curvature, can be computed directly from motion disparities, without the computation of an exact depth map or the directions of surface normals. I show that humans can judge the curvature sense of three points undergoing 3D motion from two, three and four views with success rate significantly above chance. A simple RBF net has been trained to perform the same task.
Original languageEnglish
Title of host publicationNIPS 1990
EditorsRichard P. Lippmann
PublisherMorgan Kaufmann Publishers, Inc.
Number of pages7
ISBN (Print)9781558601840
StatePublished - 1990
Event4th IEEE Conference on Neural Information Processing Systems, NIPS 1990 - Denver, United States
Duration: 26 Nov 199029 Nov 1990
Conference number: 4

Publication series

NameAdvances in Neural Information Processing Systems
PublisherMorgan Kaufmann Publishers
ISSN (Print)1049-5258


Conference4th IEEE Conference on Neural Information Processing Systems, NIPS 1990
Abbreviated titleNIPS 1990
Country/TerritoryUnited States

Cite this