Stereo matching with linear superposition of layers

Spacetime Stereo and 3D Flow via Binocular Spatiotemporal Orientation Analysis

This paper presents a novel approach to recovering estimates of 3D structure and motion of a dynamic scene from a sequence of binocular stereo images. The approach is based on matching spatiotemporal orientation distributions between left and right temporal image streams, which encapsulates both local spatial and temporal structure for disparity estimation. By capturing spatial and temporal structure in this unified fashion, both sources of information combine to yield disparity estimates that are naturally temporal coherent, while helping to resolve matches that might be ambiguous when either source is considered alone. Further, by allowing subsets of the orientation measurements to support different disparity estimates, an approach to recovering multilayer disparity from spacetime stereo is realized. Similarly, the matched distributions allow for direct recovery of dense, robust estimates of 3D scene flow. The approach has been implemented with real-time performance on commodity GPUs using OpenCL. Empirical evaluation shows that the proposed approach yields qualitatively and quantitatively superior estimates in comparison to various alternative approaches, including the ability to provide accurate multilayer estimates in the presence of (semi)transparent and specular surfaces.

Blind Separation of Superimposed Moving Images Using Image Statistics

We address the problem of blind separation of multiple source layers from their linear mixtures with unknown mixing coefficients and unknown layer motions. Such mixtures can occur when one takes photos through a transparent medium, like a window glass, and the camera or the medium moves between snapshots. To understand how to achieve correct separation, we study the statistics of natural images in the Labelme data set. We not only confirm the well-known sparsity of image gradients, but also discover new joint behavior patterns of image gradients. Based on these statistical properties, we develop a sparse blind separation algorithm to estimate both layer motions and linear mixing coefficients and then recover all layers. This method can handle general parameterized motions, including translations, scalings, rotations, and other transformations. In addition, the number of layers is automatically identified, and all layers can be recovered, even in the underdetermined case where mixtures are fewer than layers. The effectiveness of this technology is shown in experiments on both simulated and real superimposed images.

Inversion by P4: polarization-picture post-processing

Polarization may be sensed by imaging modules. This is done in various engineering systems as well as in biological systems, specifically by insects and some marine species. However, polarization per pixel is usually not the direct variable of interest. Rather, polarization-related data serve as a cue for recovering task-specific scene information. How should polarization-picture post-processing (P(4)) be done for the best scene understanding? Answering this question is not only helpful for advanced engineering (computer vision), but also to prompt hypotheses as to the processing occurring within biological systems. In various important cases, the answer is found by a principled expression of scene recovery as an inverse problem. Such an expression relies directly on a physics-based model of effects in the scene. The model includes analysis that depends on the different polarization components, thus facilitating the use of these components during the inversion, in a proper, even if non-trivial, manner. We describe several examples for this approach. These include automatic removal of path radiance in haze or underwater, overcoming partial semireflections and visual reverberations; three-dimensional recovery and distance-adaptive denoising. The resulting inversion algorithms rely on signal-processing methods, such as independent component analysis, deconvolution and optimization.

A convex optimization approach for depth estimation under illumination variation

Illumination changes cause serious problems in many computer vision applications. We present a new method for addressing robust depth estimation from a stereo pair under varying illumination conditions. First, a spatially varying multiplicative model is developed to account for brightness changes induced between left and right views. The depth estimation problem, based on this model, is then formulated as a constrained optimization problem in which an appropriate convex objective function is minimized under various convex constraints modelling prior knowledge and observed information. The resulting multiconstrained optimization problem is finally solved via a parallel block iterative algorithm which offers great flexibility in the incorporation of several constraints. Experimental results on both synthetic and real stereo pairs demonstrate the good performance of our method to efficiently recover depth and illumination variation fields, simultaneously.

Blind separation of superimposed shifted images using parameterized joint diagonalization

We consider the blind separation of source images from linear mixtures thereof, involving different relative spatial shifts of the sources in each mixture. Such mixtures can be caused, e.g., by the presence of a semi-reflective medium (such as a window glass) across a photographed scene, due to slight movements of the medium (or of the sources) between snapshots. Classical separation approaches assume either a static mixture model or a fully convolutive mixture model, which are, respectively, either under- or over-parameterized for this problem. In this paper, we develop a specially parameterized scheme for approximate joint diagonalization of estimated spectrum matrices, aimed at estimating the succinct set of mixture parameters: the static (gain) coefficients and the shift values. The estimated parameters are, in turn, used for convenient frequency-domain separation. As we demonstrate using both synthetic mixtures and real-life photographs, the advantage of the ability to incorporate spatial shifts is twofold: Not only does it enable separation when such shifts are present, but it also warrants deliberate introduction of such shifts as a simple source of added diversity whenever the static mixing coefficients form a singular matrix-thereby enabling separation in otherwise inseparable scenes.

Entropy-controlled quadratic markov measure field models for efficient image segmentation

We present a new Markov random field (MRF) based model for parametric image segmentation. Instead of directly computing a label map, our method computes the probability that the observed data at each pixel is generated by a particular intensity model. Prior information about segmentation smoothness and low entropy of the probability distribution maps is codified in the form of a MRF with quadratic potentials so that the optimal estimator is obtained by solving a quadratic cost function with linear constraints. Although, for segmentation purposes, the mode of the probability distribution at each pixel is naturally used as an optimal estimator, our method permits the use of other estimators, such as the mean or the median, which may be more appropriate for certain applications. Numerical experiments and comparisons with other published schemes are performed, using both synthetic images and real data of brain MRI for which expert hand-made segmentations are available. Finally, we show that the proposed methodology may be easily extended to other problems, such as stereo disparity estimation.