Reconstruction an object's shape from its appearance manifold under moving light (コンピュータビジョンとイメージメディア)
スポンサーリンク
概要
- 論文の詳細を見る
This paper presents a technique for recovering the shape of an object from its appearance manifold composed of a set of images that can be taken from a fixed viewpoint camera under a moving light source. We assume the distant illumination, a convex object shape and the variations of the object's appearance under a moving light are caused by the difference in the surface normals. These input images give an appearance manifold and a dimensionality reduction technique called 'Isomap' can recover the embedding three-dimensional surface normals of the object from this appearance manifold. Furthermore, the boundary points are used as the reference points to transform the result three-dimensional vectors into the true distribution of the surface normals. The proposed method is available for a wide range of reflectance materials and is easy to implement. The only requirement for our method is to take the different images of an object under different lighting directions.
- 一般社団法人情報処理学会の論文
- 2007-03-19
著者
-
Okabe Takahiro
Institute of Industrial Science, The University of Tokyo
-
Sato Yoichi
Institute of Industrial Science, The University of Tokyo
-
Okabe Takahiro
Univ. Of Tokyo
-
Sato Imari
NII
-
Sato Yoichi
Univ. of Tokyo
-
Qiong Yu
Institute of Industrial Science, The University of Tokyo
-
Sato Imari
Institute of Industrial Science, The University of Tokyo
-
Qiong Yu
Institute Of Industrial Science The University Of Tokyo
-
Sato Yoichi
University Of Tokyo
-
Sato Yoichi
Institute For Molecular Science
-
Yu Qiong
Institute of Industrial Science, The University of Tokyo
関連論文
- Reflectance Estimation under Complex Illumination
- Manifold-based photometric stereo with cast shadows (コンピュータビジョンとイメージメディア)
- Manifold-based photometric stereo with cast shadows (パターン認識・メディア理解)
- Manifold-based photometric stereo with cast shadows (画像工学)
- Reconstruction an object's shape from its appearance manifold under moving light (コンピュータビジョンとイメージメディア)
- Tracking People in Crowds by Feature Point Cluster Analysis Based on Spatial and Frequency Domain Cues
- Laser Emission under ^4F_ and ^4F_ Pumping in Nd : LSB Micro-Laser
- Aesthetic Quality Classification of Photographs
- 環境への自動適応を伴うアピアランスベース頭部姿勢推定
- 環境への自動適応を伴うアピアランスベース頭部姿勢推定
- Automatic Radiometric Calibration in Photometric Stereo by Using Irradiance Consistency
- Automatic Radiometric Calibration in Photometric Stereo by Using Irradiance Consistency
- Segmentation of the Speaker's Face Region with Audiovisual Correlation
- Joint Estimation of Facial Pose and Expression Using Variable-Intensity Templates
- On the in situ estimation of surface acoustic impedance in interiors of arbitrary shape by acoustical inverse methods
- Modeling and Recognizing Human Activities from Video
- An MDL Approach to Learning Activity Grammars(Gestures)
- 環境への自動適応を伴うアピアランスベース頭部姿勢推定(テーマセッション,コンピュータビジョンとパターン認識のための機械学習)
- 環境への自動適応を伴うアピアランスベース頭部姿勢推定(テーマセッション,コンピュータビジョンとパターン認識のための機械学習)
- Driving Feature Extraction from High and Low Skilled Drivers in Curve Sections Based on Machine Learning
- Optimal Sampling for Efficient BRDF Acquisition
- Optimal Sampling for Efficient BRDF Acquisition