This paper presents a stereo algorithm for obtaining disparity maps with occlusion explicitly detected. To produce smooth and detailed disparity maps, two assumptions that were originally proposed by Marr and Poggio are adopted: uniqueness and continuity. That is, the disparity maps have a unique value per pixel and are continuous almost everywhere. These assumptions are enforced within a three-dimensional array of match values in disparity space. Each match value corresponds to a pixel in an image and a disparity relative to another image. An iterative algorithm updates the match values by diffusing support among neighboring values and inhibiting others along similar lines of sight. By applying the uniqueness assumption, occluded regions can be explicitly identified. To demonstrate the effectiveness of the algorithm we present the processing results from synthetic and real image pairs, including ones with ground-truth values for quantitative comparison with other method.

Digital photographs and video are exciting inventions that let us capture the visual experience of events around us in a computer and re-live the experience, although in a restrictive manner. Photographs only capture snapshots of a dynamic event, and while video does capture motion, it is recorded from pre-determined positions and consists of images discretely sampled in time, so the timing cannot be changed.

Contents 1 Introduction 7 1.1 Thesis Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 1.2 General Overview of the City Scanning Project . . . . . . . . . . . . . . . . 8 1.2.1 The Pipeline . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 1.2.2 Acquisition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 1.2.3 Pose Refinement . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10 1.2.4 Facade Extraction . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10 1.2.5 Input data and Objectives . . . . . . . . . . . . . . . . . . . . . . . . 11 2 Texture Estimation 12 2.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12 2.1.1 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12 2.1.2 Related Work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13 2.1.3 Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . .

of the Dissertation Integration of Focus and Defocus Analysis with Color Stereo for Three-Dimensional Shape Recovery by Ta Yuan Doctor of Philosophy in Electrical Engineering State University of New York at Stony Brook 1999 Recovering the 3D (three-dimensional) shape of objects in a scene is an important topic in computer vision. Several methods including passive and active methods are developed to investigate this topic. Two kinds of information are recovered during the 3D shape recovery. One is the geometric information about the shape of the object. The other is the photometric information about the light energy distribution on the object surface. One effective method is developed in this research and its algorithms and results are presented in this dissertation. The method developed in this research integrates three important techniques in machine vision IFA (Image Focus Analysis), IDA (Image Defocus Analysis), and SIA iv (Stereo Image Analysis). IDA is used to fast d...

We present a new approach to combine two approaches to three-dimensional reconstruction: silhouette-based and correspondence-based approaches. The two approaches have complementary costs and benefits. Silhouette-based approaches deliver volumetric descriptions which often have very few outliers, but they cannot reconstruct concave surfaces. Correspondence-based approaches give surface descriptions with sub-pixel accuracy, but their search range either allows outliers or falls short of the correct match. We show that a combination of the two can deliver fine-grained accuracy with few outliers. Our specific implementation uses the silhouette reconstruction as prior data to center and bound a stereo search process. We explore the different performance characteristics of the combination and its two component methods qualitatively and quantitatively using real imagery.