A layered approach to stereo reconstruction
- 27 November 2002
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 434-441
- https://doi.org/10.1109/cvpr.1998.698642
Abstract
We propose a framework for extracting structure from stereo which represents the scene as a collection of approx- imately planar layers. Each layer consists of an explicit 3D plane equation, a colored image with per-pixel opac- ity (a sprite), and a per-pixel depth offset relative to the plane. Initial estimates of the layers are recovered using techniques taken from parametric motion estimation. These initial estimates are then refined using a re-synthesis algo- rithm which takes into account both occlusions and mixed pixels. Reasoning about such effects allows the recovery of depth and color information with high accuracy, even in partially occluded regions. Another important benefit of our framework is that the output consists of a collection of approximately planar regions, a representation which is far more appropriate than a dense depth map for many appli- cations such as rendering and video parsing.Keywords
This publication has 30 references indexed in Scilit:
- Layered representation for motion analysisPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Local, global, and multilevel stereo matchingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Accurate computation of optical flow by using layered motion representationsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Stereo matching with transparency and mattingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Smoothness in layers: Motion segmentation using nonparametric mixture estimationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Creating full view panoramic image mosaics and environment mapsPublished by Association for Computing Machinery (ACM) ,1997
- TalismanPublished by Association for Computing Machinery (ACM) ,1996
- Modeling and rendering architecture from photographsPublished by Association for Computing Machinery (ACM) ,1996
- A unified mixture framework for motion segmentation: incorporating spatial coherence and estimating the number of modelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1996
- Disparity-space images and large occlusion stereoPublished by Springer Nature ,1994