This book constitutes the strictly refereed post-workshop proceedings of the European Workshop on 3D Structure from Multiple Images of Large-Scale Environments, SMILE'98, held in conjunction with ECCV'98 in Freiburg, Germany, in June 1998. The 21 revised full papers presented went through two cycles of reviewing and were carefully selected for inclusion in the book. The papers are organized in sections on multiview relations and correspondence search, 3D structure from multiple images, callibration and reconstruction using scene constraints, range integration and augmented reality application.

The issue discusses methods to extract 3-dimensional (3D) models from plain images. In particular, the 3D information is obtained from images for which the camera parameters are unknown. The principles underlying such uncalibrated structure-from-motion methods are outlined. First, a short review of 3D acquisition technologies puts such methods in a wider context, and highlights their important advantages. Then, the actual theory behind this line of research is given. The authors have tried to keep the text maximally self-contained, therefore also avoiding to rely on an extensive knowledge of the projective concepts that usually appear in texts about self-calibration 3D methods. Rather, mathematical explanations that are more amenable to intuition are given. The explanation of the theory includes the stratification of reconstructions obtained from image pairs as well as metric reconstruction on the basis of more than 2 images combined with some additional knowledge about the cameras used. Readers who want to obtain more practical information about how to implement such uncalibrated structure-from-motion pipelines may be interested in two more Foundations and Trends issues written by the same authors. Together with this issue they can be read as a single tutorial on the subject.

Computational methodologies of signal processing and imaging analysis, namely considering 2D and 3D images, are commonly used in different applications of the human society. For example, Computational Vision systems are progressively used for surveillance tasks, traf?c analysis, recognition process, inspection p- poses, human-machine interfaces, 3D vision and deformation analysis. One of the main characteristics of the Computational Vision domain is its int- multidisciplinary. In fact, in this domain, methodologies of several more fundam- tal sciences, such as Informatics, Mathematics, Statistics, Psychology, Mechanics and Physics are usually used. Besides this inter-multidisciplinary characteristic, one of the main reasons that contributes for the continually effort done in this domain of the human knowledge is the number of applications in the medical area. For instance, it is possible to consider the use of statistical or physical procedures on medical images in order to model the represented structures. This modeling can have different goals, for example: shape reconstruction, segmentation, registration, behavior interpretation and simulation, motion and deformation analysis, virtual reality, computer-assisted therapy or tissue characterization. The main objective of the ECCOMAS Thematic Conferences on Computational Vision and Medical Image Processing (VIPimage) is to promote a comprehensive forum for discussion on the recent advances in the related ?elds trying to id- tify widespread areas of potential collaboration between researchers of different sciences.

This volume contains the ?nal version of the papers originally presented at the second SMILE workshop 3D Structure from Multiple Images of Large-scale Environments, which was held on 1-2 July 2000 in conjunction with the Sixth European Conference in Computer Vision at Trinity College Dublin. The subject of the workshop was the visual acquisition of models of the 3D world from images and their application to virtual and augmented reality. Over the last few years tremendous progress has been made in this area. On the one hand important new insightshavebeenobtainedresultinginmore exibilityandnewrepresentations.Onthe other hand a number of techniques have come to maturity, yielding robust algorithms delivering good results on real image data. Moreover supporting technologies – such as digital cameras, computers, disk storage, and visualization devices – have made things possible that were infeasible just a few years ago. Opening the workshop was Paul Debevec s invited presentation on image-based modeling,rendering,andlighting.Hepresentedanumberoftechniquesforusingdigital images of real scenes to create 3D models, virtual camera moves, and realistic computer animations.Theremainderoftheworkshopwasdividedintothreesessions:Computation and Algorithms, Visual Scene Representations, and Extended Environments. After each session there was a panel discussion that included all speakers. These panel discussions were organized by Bill Triggs, Marc Pollefeys, and Tomas Pajdla respectively, who introduced the topics and moderated the discussion. Asubstantialpartoftheseproceedingsarethetranscriptsofthediscussionsfollowing each paper and the full panel sessions. These discussions were of very high quality and were an integral part of the workshop.

This book formalizes and analyzes the relations between multiple views of a scene from the perspective of various types of geometries. A key feature is that it considers Euclidean and affine geometries as special cases of projective geometry. Over the last forty years, researchers have made great strides in elucidating the laws of image formation, processing, and understanding by animals, humans, and machines. This book describes the state of knowledge in one subarea of vision, the geometric laws that relate different views of a scene. Geometry, one of the oldest branches of mathematics, is the natural language for describing three-dimensional shapes and spatial relations. Projective geometry, the geometry that best models image formation, provides a unified framework for thinking about many geometric problems are relevant to vision. The book formalizes and analyzes the relations between multiple views of a scene from the perspective of various types of geometries. A key feature is that it considers Euclidean and affine geometries as special cases of projective geometry. Images play a prominent role in computer communications. Producers and users of images, in particular three-dimensional images, require a framework for stating and solving problems. The book offers a number of conceptual tools and theoretical results useful for the design of machine vision algorithms. It also illustrates these tools and results with many examples of real applications.