Perception of 3-D surfaces from 2-D contours
- 1 January 1993
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 15 (1), 3-18
- https://doi.org/10.1109/34.184771
Abstract
Inference of 3-D shape from 2-D contours in a single image is an important problem in machine vision. We survey classes of techniques proposed in the past and provide a critical analysis. We propose that two kinds of symmetries in figures, which are known as parallel and skew symmetries, give significant information about surface shape for a variety of objects. We derive the constraints imposed by these symmetries and show how to use them to infer 3-D shape. We discuss the zero Gaussian curvature (ZGC) surfaces in depth and show results on the recovery of surface orientation for various ZGC surfaces. © 1993 IEEKeywords
This publication has 19 references indexed in Scilit:
- Perception of 3-D surfaces from 2-D contoursIEEE Transactions on Pattern Analysis and Machine Intelligence, 1993
- Invariant properties of straight homogeneous generalized cylinders and their contoursIEEE Transactions on Pattern Analysis and Machine Intelligence, 1989
- Line-drawing interpretation: bilateral symmetryIEEE Transactions on Pattern Analysis and Machine Intelligence, 1989
- On the geometric interpretation of image contoursArtificial Intelligence, 1988
- 3D shape representation by contoursComputer Vision, Graphics, and Image Processing, 1988
- Corner detection and curve representation using cubic B-splinesComputer Vision, Graphics, and Image Processing, 1987
- What Does the Occluding Contour Tell Us about Solid Shape?Perception, 1984
- Gradient space under orthography and perspectiveComputer Vision, Graphics, and Image Processing, 1983
- The visual interpretation of surface contoursArtificial Intelligence, 1981
- Interpreting pictures of polyhedral scenesArtificial Intelligence, 1973