HMM-based surface reconstruction from single images

Takayuki Nagai, Tadashi Naruse, Masaaki Ikehara, Akira Kurematsu

研究成果: Paper査読

35 被引用数 (Scopus)


In this paper, a novel method of the surface reconstruction from a single monocular image is proposed. Our proposed approach (called shape from knowledge) is based on the knowledge of objects, which is acquired by learning from a number of samples. To achieve this, we investigate making use of the Hidden Markov Model (HMM) framework, which models the correspondence between an intensity image and its depth information. We have applied our algorithm to the 3-D face and 3-D hand reconstruction from single images, and the results show the effectiveness of the proposed method.

出版ステータスPublished - 2002 1月 1
イベントInternational Conference on Image Processing (ICIP'02) - Rochester, NY, United States
継続期間: 2002 9月 222002 9月 25


OtherInternational Conference on Image Processing (ICIP'02)
国/地域United States
CityRochester, NY

ASJC Scopus subject areas

  • ハードウェアとアーキテクチャ
  • コンピュータ ビジョンおよびパターン認識
  • 電子工学および電気工学


「HMM-based surface reconstruction from single images」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。