In this paper, we propose a non-stationary stochastic filtering framework for the task of albedo estimation from a single image. There are several approaches in literature for albedo estimation, but few include the errors in estimates of surface normals and light source directions to improve the albedo estimate. The proposed approach effectively utilizes the error statistics of surface normals and illumination direction for robust estimation of albedo. The albedo estimate obtained is further used to generate albedo-free normalized images for recovering the shape of an object. Illustrations and experiments are provided to show the efficacy of the approach and its application to illumination-invariant matching and shape recovery.

Most shape matching methods are either fast but too simplistic to give the desired performance or promising as far as performance is concerned but computationally demanding. We present a very simple and efficient approach that not only performs almost as good as many state-of-the-art techniques but also scales up to large databases. In our approach, each shape is indexed based on a variety of simple and easily computable features which are invariant to articulations and rigid transformations. The features characterize pairwise geometric relationships between interest points on the shape, thereby providing robustness to the approach. Shapes are retrieved using an efficient scheme which does not involve costly operations like shape-wise alignment or establishing correspondences.

Given any two images with different illumination conditions, there always exist a physically realizable object which is consistent with both the images even if the lighting in each scene is constrained to be a known point light source at infinity. We show that images are much less ambiguous for the class of bilaterally symmetric Lambertian objects. In fact, the set of such objects can be partitioned into equivalence classes such that it is always possible to distinguish between two objects belonging to different equivalence classes using just one image per object. The conditions required for two objects to belong to the same equivalence class are very restrictive, thereby leading to the conclusion that images of symmetric objects are hardly ambiguous. The observation leads to an illumination-invariant matching algorithm to compare images of bilaterally symmetric Lambertian objects.

Though implicit representations of surfaces have often been used for various computer graphics tasks like modeling and morphing of objects, it has rarely been used for registration and matching of 3D point clouds. Unlike in graphics, where the goal is precise reconstruction, we use isosurfaces to derive a smooth and approximate representation of the underlying point cloud which helps in generalization. Implicit surfaces are generated using a variational interpolation technique. Implicit function values on a set of concentric spheres around the 3D point cloud of object are used as features for matching. Geometric-invariance is achieved by decomposing implicit values based feature set into various spherical harmonics. The decomposition provides a compact representation of 3D point clouds while achieving rotation invariance.

The problem in computer vision of inferring the illumination direction is well studied for digital photographs of natural scenes and recently has become important in the study of realist art as well. We extend previous work on this topic in several ways, testing our methods on Jan Vermeer’s Girl with a pearl earring (c. 1665–1666). We use both model-independent methods (cast-shadow analysis, occluding-contour analysis) and model-based methods (physical models of the pearl, of the girl’s eyes, of her face). Some of these methods provide an estimate of the illuminant position in the three dimensions of the picture space, others in just the two dimensions of the picture plane. Our key contributions are a Bayesian evidence integration scheme for such disparate sources of information and an empirical demonstration of the agreement, or at least consistency, among such estimates in a realist painting. Our methods may be useful to humanist art scholars addressing a number of technical problems in the history of art.

Human faces undergo a lot of change in appearance as they age. Though facial aging has been studied for decades, it is only recently that attempts have been made to address the problem from a computational point of view. Most of these early efforts follow a simulation approach in which matching is performed by synthesizing face images at the target age. Given the innumerable different ways in which a face can potentially age, the synthesized aged image may not be similar to the actual aged image. In this work, we make an attempt to bypass the synthesis step and analyze various aging effects directly from a matching perspective. In particular, we analyze drifts of facial features with aging. Our analysis is based on the observation that facial appearance changes in a coherent manner as people age. We provide measures to capture this coherency in feature drifts. Illustrations and experimental results show the efficacy of such an approach for matching faces across age progression.

In this work, we address the problem of separating the diffuse and specular reflectance components of complex textured surfaces from a single color image. We first develop a Hough transform based approach for automatic estimation of illumination source color from the image. Using the estimated source color, the diffuse and specular components of a color pixel are separated by projecting the RGB vector along the corresponding diffuse color direction and illumination source color direction respectively. In the absence of purely diffuse pixels, the proposed algorithm returns a more diffuse version of the input image. The approach is completely automatic and does not need explicit color segmentation or color boundary detection.