What Is the Set of Images of an Object Under All Possible Illumination Conditions?
International Journal of Computer Vision
CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)
Diffusion maps clustering for magnetic resonance Q-ball imaging segmentation
Journal of Biomedical Imaging - Recent Advances in Neuroimaging Methodology
Manifold models for signals and images
Computer Vision and Image Understanding
Finding representative landmarks of data on manifolds
Pattern Recognition
Texture synthesis and modification with a patch-valued wavelet transform
SSVM'07 Proceedings of the 1st international conference on Scale space and variational methods in computer vision
Semi-supervised learning with varifold Laplacians
Neurocomputing
Joint manifolds for data fusion
IEEE Transactions on Image Processing - Special section on distributed camera networks: sensing, processing, communication, and implementation
Geodesic Methods in Computer Vision and Graphics
Foundations and Trends® in Computer Graphics and Vision
Learning colours from textures by sparse manifold embedding
AI'11 Proceedings of the 24th international conference on Advances in Artificial Intelligence
Isometric Embeddings in Imaging and Vision: Facts and Fiction
Journal of Mathematical Imaging and Vision
Efficient point-to-subspace query in ℓ1 with application to robust face recognition
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part IV
Learning colours from textures by sparse manifold embedding
Signal Processing
Hi-index | 0.00 |
Recently, the Isomap procedure [10] was proposed as a new way to recover a low-dimensional parametrization of data lying on a low-dimensional submanifold in high-dimensional space. The method assumes that the submanifold, viewed as a Riemannian submanifold of the ambient high-dimensional space, is isometric to a convex subset of Euclidean space. This naturally raises the question: what datasets can reasonably be modeled by this condition? In this paper, we consider a special kind of image data: families of images generated by articulation of one or several objects in a scene--for example, images of a black disk on a white background with center placed at a range of locations. The collection of all images in such an articulation family, as the parameters of the articulation vary, makes up an articulation manifold, a submanifold of L2. We study the properties of such articulation manifolds, in particular, their lack of differentiability when the images have edges. Under these conditions, we show that there exists a natural renormalization of geodesic distance which yields a well-defined metric. We exhibit a list of articulation models where the corresponding manifold equipped with this new metric is indeed isometric to a convex subset of Euclidean space. Examples include translations of a symmetric object, rotations of a closed set, articulations of a horizon, and expressions of a cartoon face.The theoretical predictions from our study are borne out by empirical experiments with published Isomap code. We also note that in the case where several components of the image articulate independently, isometry may fail; for example, with several disks in an image avoiding contact, the underlying Riemannian manifold is locally isometric to an open, connected, but not convex subset of Euclidean space. Such a situation matches the assumptions of our recently-proposed Hessian Eigenmaps procedure, but not the original Isomap procedure.