An efficient hole-filling approach using adaptive rendering

Chao Ho Chen, Chun Yi Sung, Tsong Yi Chen, Bo Ting Guo, Chin-Hsing Chen

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

1 Citation (Scopus)

Abstract

Based on depth image based rendering (DIBR), this paper presents an efficient hole-filling approach using adaptive rendering for the 2D-to-3D conversion system, i.e., converting monocular image to multi-view virtual images. The traditional processing of DIBR includes depth map pre-processing, image 3D warping, and hole-filling. The depth map pre-processing stage is mainly dedicated to reduction of holes, but it will bring about geometric distortion and texture artifacts. Therefore, an efficient hole filling approach without the depth-map preprocessing is motivated for enhancing the quality of multi-view virtual images. The adaptive rendering strategy is employed to find the appropriate block for performing hole-filling process. Experimental results show that the proposed approach is superior in hole-filling ability to other methods.

Original languageEnglish
Title of host publicationProceedings - 2012 6th International Conference on Genetic and Evolutionary Computing, ICGEC 2012
Pages336-339
Number of pages4
DOIs
Publication statusPublished - 2012 Dec 1
Event2012 6th International Conference on Genetic and Evolutionary Computing, ICGEC 2012 - Kitakyushu, Japan
Duration: 2012 Aug 252012 Aug 28

Publication series

NameProceedings - 2012 6th International Conference on Genetic and Evolutionary Computing, ICGEC 2012

Other

Other2012 6th International Conference on Genetic and Evolutionary Computing, ICGEC 2012
Country/TerritoryJapan
CityKitakyushu
Period12-08-2512-08-28

All Science Journal Classification (ASJC) codes

  • Biochemistry, Genetics and Molecular Biology(all)

Fingerprint

Dive into the research topics of 'An efficient hole-filling approach using adaptive rendering'. Together they form a unique fingerprint.

Cite this