Photorealistic Texturing of Human Busts Reconstructions - 16.225

C. Heindl et al., "Photorealistic Texturing of Human Busts Reconstructions", in Proc. of 7th Int. Conf. on 3D Body Scanning Technologies, Lugano, Switzerland, 2016, pp. 225-230, https://doi.org/10.15221/16.225.

Title:

Photorealistic Texturing of Human Busts Reconstructions

Authors:

Christoph HEINDL, Sharath Chandra AKKALADEVI, Harald BAUER

PROFACTOR GmbH, Steyr, Austria

Abstract:

Recent developments in the RGBD sensors systems, lead to a new generation of sensors providing high quality color images along with moderate depth resolution images. Most state-of-the-art real-time reconstruction algorithms support colorized reconstruction by methods that rely on vertex colorization. However, the resolution of vertex colorization is directly linked to mesh resolution. High quality color images therefore require an enormous amount of vertices in order to capture image details. This leads to unattractive large model files, large memory consumption and long processing times. In this work we propose an automated pipeline that is able to texture low-resolution geometric meshes with high quality color images. Experiments evaluate the proposed method in challenging environments such as varying illumination and non-rigid reconstructions.

Details:

Full paper: 16.225.pdf
Proceedings: 3DBST 2016, 30 Nov.-1 Dec. 2016, Lugano, Switzerland
Pages: 225-230
DOI: 10.15221/16.225

License/Copyright notice:

Proceedings: © Hometrica Consulting - Dr. Nicola D'Apuzzo, Switzerland, hometrica.ch.
Authors retain all rights to individual papers, which are licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
The papers appearing in the proceedings reflect the author's opinions. Their inclusion in the proceedings does not necessary constitute endorsement by the editor or by the publisher.


Note: click the + on the top left of the page to open/close the menu.