Compensated Visual Hull with GPU-Based Optimization

  • Authors:
  • Hansung Kim;Ryuuki Sakamoto;Itaru Kitahara;Tomoji Toriyama;Kiyoshi Kogure

  • Affiliations:
  • CVSSP, FEPS, University of Surrey, Guildford, UK GU2 7XH and Knowledge Science Lab, ATR, Kyoto, Japan 619-0288;Knowledge Science Lab, ATR, Kyoto, Japan 619-0288 and Faculty of Systems Engineering, Wakayama University, Japan;Knowledge Science Lab, ATR, Kyoto, Japan 619-0288 and Dept. of Intelligent Interaction Technologies, University of Tsukuba, Japan;Knowledge Science Lab, ATR, Kyoto, Japan 619-0288 and Dept. of Information System Engineering, Toyama Prefectural University, Japan;Knowledge Science Lab, ATR, Kyoto, Japan 619-0288

  • Venue:
  • PCM '08 Proceedings of the 9th Pacific Rim Conference on Multimedia: Advances in Multimedia Information Processing
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

We propose an advanced visual hull technique to compensate for outliers using the reliabilities of silhouettes. The proposed method consists of a foreground extraction technique with multiple thresholds based on the Generalized Gaussian Family model and a compensated visual hull algorithm. We proved that the proposed technique constructs a compact visual hull even in the presence of segmentation errors and occlusions. The 3D reconstruction and rendering processes are implemented on a graphics processing unit to greatly accelerate computation time.