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 22 → 2002 9月 25
|Other||International Conference on Image Processing (ICIP'02)|
|Period||02/9/22 → 02/9/25|
ASJC Scopus subject areas
- コンピュータ ビジョンおよびパターン認識