Qualitative Structure from Motion

Abstract

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 com(cid:173) puted 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.

Cite

Text

Weinshall. "Qualitative Structure from Motion." Neural Information Processing Systems, 1990.

Markdown

[Weinshall. "Qualitative Structure from Motion." Neural Information Processing Systems, 1990.](https://mlanthology.org/neurips/1990/weinshall1990neurips-qualitative/)

BibTeX

@inproceedings{weinshall1990neurips-qualitative,
  title     = {{Qualitative Structure from Motion}},
  author    = {Weinshall, Daphna},
  booktitle = {Neural Information Processing Systems},
  year      = {1990},
  pages     = {356-362},
  url       = {https://mlanthology.org/neurips/1990/weinshall1990neurips-qualitative/}
}