Principal Warps: Thin-Plate Splines and the Decomposition of Deformations
IEEE Transactions on Pattern Analysis and Machine Intelligence
Recognition by Linear Combinations of Models
IEEE Transactions on Pattern Analysis and Machine Intelligence - Special issue on interpretation of 3-D scenes—part I
Geometry and photometry in three-dimensional visual recognition
Geometry and photometry in three-dimensional visual recognition
The Space Requirements of Indexing Under Perspective Projections
IEEE Transactions on Pattern Analysis and Machine Intelligence
On the Geometry of Visual Correspondence
International Journal of Computer Vision
On Photometric Issues in 3D Visual Recognition from aSingle 2D Image
International Journal of Computer Vision
What Is the Set of Images of an Object Under All Possible Illumination Conditions?
International Journal of Computer Vision
IEEE Transactions on Pattern Analysis and Machine Intelligence
Lambertian Reflectance and Linear Subspaces
IEEE Transactions on Pattern Analysis and Machine Intelligence
Face Recognition Based on Fitting a 3D Morphable Model
IEEE Transactions on Pattern Analysis and Machine Intelligence
The CMU Pose, Illumination, and Expression Database
IEEE Transactions on Pattern Analysis and Machine Intelligence
Appearance-Based Face Recognition and Light-Fields
IEEE Transactions on Pattern Analysis and Machine Intelligence
Face Recognition Based on Frontal Views Generated from Non-Frontal Images
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Tied Factor Analysis for Face Recognition across Large Pose Differences
IEEE Transactions on Pattern Analysis and Machine Intelligence
Hi-index | 0.00 |
The appearance of a 3D object depends on both the viewing directions and illumination conditions. It is proven that all n-pixel images of a convex object with Lambertian surface under variable lighting from infinity form a convex polyhedral cone (called illumination cone) in n-dimensional space. This paper tries to answer the other half of the question: What is the set of images of an object under all viewing directions? A novel image representation is proposed, which transforms any n-pixel image of a 3D object to a vector in a 2n-dimensional pose space. In such a pose space, we prove that the transformed images of a 3D object under all viewing directions form a parametric manifold in a 6-dimensional linear subspace. With in-depth rotations along a single axis in particular, this manifold is an ellipse. Furthermore, we show that this parametric pose manifold of a convex object can be estimated from a few images in different poses and used to predict object's appearances under unseen viewing directions. These results immediately suggest a number of approaches to object recognition, scene detection, and 3D modelling. Experiments on both synthetic data and real images were reported, which demonstrates the validity of the proposed representation.