Abstract.  We present a passive computer vision method that exploits existing mapping and navigation databases in order to automatically create 3D building models. Our method defines a grammar for representing changes in building geometry that approximately follow the Manhattan-world assumption which states there is a predominance of three mutually orthogonal directions in the scene. By using multiple calibrated aerial images, we extend previous Manhattan-world methods to robustly produce a single, coherent, complete geometric model of a building with partial textures. Our method uses an optimization to discover a 3D building geometry that produces the same set of façade orientation changes observed in the captured images. We have applied our method to several real-world buildings and have analyzed our approach using synthetic buildings.

Abstract.  We present an important step towards the solution of the problem of inverse procedural modeling by generating parametric context-free L-systems that represent an input 2D model. The L-system rules efficiently code the regular structures and the parameters represent the properties of the structure transformations. The algorithm takes as input a 2D vector image that is composed of atomic elements, such as curves and poly-lines. Similar elements are recognized and assigned terminal symbols of an L-system alphabet. The terminal symbols’ position and orientation are pair-wise compared and the transformations are stored as points in multiple 4D transformation spaces. By careful analysis of the clusters in the transformation spaces, we detect sequences of elements and code them as L-system rules. The coded elements are then removed from the clusters, the clusters are updated, and then the analysis attempts to code groups of elements in (hierarchies) the same way. The analysis ends with a single group of elements that is coded as an L-system axiom. We recognize and code branching sequences of linearly translated, scaled, and rotated elements and their hierarchies. The L-system not only represents the input image, but it can also be used for various editing operations. By changing the L-system parameters, the image can be randomized, symmetrized, and groups of elements and regular structures can be edited. By changing the terminal and non-terminal symbols, elements or groups of elements can be replaced.

Abstract.  We present an interactive system for synthesizing urban layouts by example. Our method simultaneously performs both a structure-based synthesis and an image-based synthesis to generate a complete urban layout with a plausible street network and with aerial-view imagery. Our approach uses the structure and image data of real-world urban areas and a synthesis algorithm to provide several high-level operations to easily and interactively generate complex layouts by example. The user can create new urban layouts by a sequence of operations such as join, expand, and blend without being concerned about low-level structural details. Further, the ability to blend example urban layout fragments provides a powerful way to generate new synthetic content. We demonstrate our system by creating urban layouts using example fragments from several real-world cities, each ranging from hundreds to thousands of city blocks and parcels.

Abstract.  The ability to create and edit a model of a large-scale city is necessary for a variety of applications. Although the layout of the  urban space is captured as images, it consists of a complex collection of man-made structures arranged in parcels, city blocks, and neighborhoods. Editing the content as unstructured images yields undesirable results. However, most GIS maintain and provide digital records of metadata such as road network, land use, parcel boundaries, building type, water/sewage pipes and power lines that can be used as a starting point to infer and manipulate higher-level structure. We describe an editor for interactive reconfiguration of city layouts, which provides tools to expand, scale, replace and move parcels and blocks, while efficiently exploiting their connectivity and zoning. Our results include applying the system on several cities with different urban layout by sequentially applying transformations.

Abstract.  Interactive visualization of architecture provides a way to quickly visualize existing or novel buildings and structures. Such applications require both fast rendering and an effortless input regimen for creating and changing architecture using high-level editing operations that automatically fill in the necessary details. Procedural modeling and synthesis is a powerful paradigm that yields high data-amplification and can be coupled with fast rendering techniques to quickly generate plausible details of a scene without much or any user interaction. Previously, forward generating procedural methods have been proposed where a procedure is explicitly created to generate a particular content. In this article, we present our work in inverse procedural modeling of buildings and describe how to use an extracted repertoire of building grammars to facilitate the visualization and quick modification of architectural structures and buildings. We demonstrate an interactive application where the user draws simple building blocks and using our system can automatically complete the building “in the style of” other buildings using view-dependent texture mapping or nonphotorealistic rendering techniques. Our system supports an arbitrary number of building grammars created from user subdivided building models and captured photographs. Using only edit, copy and paste metaphors, entire building styles can be altered and transferred from one building to another in a few operations, enhancing the ability to modify an existing architectural structure or to visualize a novel building in the style of others.

Abstract.  We present Build-by-Number, a technique for quickly designing architectural structures that can be rendered photorealistically at interactive rates. We combine image-based capturing and rendering with procedural modeling techniques to allow the creation of novel structures in the style of real-world structures. Starting with a simple model recovered from a sparse image set, the model is divided into feature regions, such as doorways, windows, and brick. These feature regions essentially comprise a mapping from model space to image space, and can be recombined to texture a novel model. Procedural rules for the growth and reorganization of the model are automatically derived to allow for very fast editing and design. Further, the redundancies marked by the feature labeling can be used to perform automatic occlusion replacement and color equalization in the finished scene, which is rendered using view-dependent texture mapping on standard graphics hardware. Results using four captured scenes show that a great variety of novel structures can be created very quickly once a captured scene is available, and rendered with a degree of realism comparable to the original scene.