Curvature-Based Regularization for Surface Approximation
(2012) IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012 p.1576-1583- Abstract
- We propose an energy-based framework for approximating surfaces from a cloud of point measurements corrupted by noise and outliers. Our energy assigns a tangent plane to each (noisy) data point by minimizing the squared distances to the points and the irregularity of the surface implicitly defined by the tangent planes. In order to avoid the well-known "shrinking" bias associated with first-order surface regularization, we choose a robust smoothing term that approximates curvature of the underlying surface. In contrast to a number of recent publications estimating curvature using discrete (e. g. binary) labellings with triple-cliques we use higher-dimensional labels that allows modeling curvature with only pair-wise interactions. Hence,... (More)
- We propose an energy-based framework for approximating surfaces from a cloud of point measurements corrupted by noise and outliers. Our energy assigns a tangent plane to each (noisy) data point by minimizing the squared distances to the points and the irregularity of the surface implicitly defined by the tangent planes. In order to avoid the well-known "shrinking" bias associated with first-order surface regularization, we choose a robust smoothing term that approximates curvature of the underlying surface. In contrast to a number of recent publications estimating curvature using discrete (e. g. binary) labellings with triple-cliques we use higher-dimensional labels that allows modeling curvature with only pair-wise interactions. Hence, many standard optimization algorithms (e. g. message passing, graph cut, etc) can minimize the proposed curvature-based regularization functional. The accuracy of our approach for representing curvature is demonstrated by theoretical and empirical results on synthetic and real data sets from multi-view reconstruction and stereo. (1) (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/3283289
- author
- Olsson, Carl LU and Boykov, Yuri
- organization
- publishing date
- 2012
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- pages
- 1576 - 1583
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- conference name
- IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012
- conference location
- Providence, RI, United States
- conference dates
- 2012-06-16 - 2012-06-21
- external identifiers
-
- wos:000309166201092
- scopus:84866699265
- ISSN
- 1063-6919
- DOI
- 10.1109/CVPR.2012.6247849
- language
- English
- LU publication?
- yes
- id
- 9db1ee80-3c35-4383-b8b6-cfd79c57ce52 (old id 3283289)
- date added to LUP
- 2016-04-01 14:14:05
- date last changed
- 2022-02-19 17:50:16
@inproceedings{9db1ee80-3c35-4383-b8b6-cfd79c57ce52, abstract = {{We propose an energy-based framework for approximating surfaces from a cloud of point measurements corrupted by noise and outliers. Our energy assigns a tangent plane to each (noisy) data point by minimizing the squared distances to the points and the irregularity of the surface implicitly defined by the tangent planes. In order to avoid the well-known "shrinking" bias associated with first-order surface regularization, we choose a robust smoothing term that approximates curvature of the underlying surface. In contrast to a number of recent publications estimating curvature using discrete (e. g. binary) labellings with triple-cliques we use higher-dimensional labels that allows modeling curvature with only pair-wise interactions. Hence, many standard optimization algorithms (e. g. message passing, graph cut, etc) can minimize the proposed curvature-based regularization functional. The accuracy of our approach for representing curvature is demonstrated by theoretical and empirical results on synthetic and real data sets from multi-view reconstruction and stereo. (1)}}, author = {{Olsson, Carl and Boykov, Yuri}}, booktitle = {{2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}}, issn = {{1063-6919}}, language = {{eng}}, pages = {{1576--1583}}, publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}}, title = {{Curvature-Based Regularization for Surface Approximation}}, url = {{http://dx.doi.org/10.1109/CVPR.2012.6247849}}, doi = {{10.1109/CVPR.2012.6247849}}, year = {{2012}}, }