By the same authors

Surface integration: Two statistical approaches

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Author(s)

Department/unit(s)

Publication details

Title of host publication14TH INTERNATIONAL CONFERENCE ON IMAGE ANALYSIS AND PROCESSING, PROCEEDINGS
DatePublished - 2007
Pages343-348
Number of pages6
PublisherIEEE COMPUTER SOC
Place of PublicationLOS ALAMITOS
Original languageEnglish
ISBN (Print)978-0-7695-2877-9

Abstract

In this paper we show how statistical constraints can be incorporated into the surface integration process. This problem aims to reconstruct the surface height function from a noisy field of surface normals. We propose two methods that employ a statistical model that captures variations in surface height. The first uses a coupled model that captures the variation in a training set of face surfaces in both the surface normal and surface height domain. The second is based on finding the parameters of a surface height model directly from afield of surface normals. We present experiments on ground truth face data and compare the results of the two methods with an existing surface integration technique.

    Research areas

  • SHAPE

Discover related content

Find related publications, people, projects, datasets and more using interactive charts.

View graph of relations