Publications

Material replacement has wide application throughout the entertainment industry, particularly for postproduction make-up application or wardrobe adjustment. More generally, any low-cost mock-up object can be processed to have the appearance of expensive, high-quality materials. We demonstrate a new system that allows fast, intuitive material replacement in photographs. We extend recent work in object selection and fast texture synthesis, as well as develop a novel approach to shapefrom- shading capable of handling objects with albedo changes. Each component of our system runs with interactive speed, allowing for easy experimentation and re- finement of results.

The ability to identify similarities between shapes is important for applications such as medical diagnosis, object registration and alignment, and shape retrieval. In this paper we present a method, which we call a Curvature Map, that uses surface curvature properties in a region around a point to create a unique signature for that point. These signatures can then be compared to determine the similarity of one point to another. To gather curvature information around a point we explore two techniques, rings (which use the local topology of the mesh) and Geodesic Fans (which trace geodesics along the mesh from the point). We explore a variety of comparison functions and provide experimental evidence for which ones provide the best discriminatory power. We show that Curvature Maps are both more robust and provide better discrimination than simply comparing the curvature at individual points.

Modelling by analogy has become a powerful paradigm for editing images. Using a pair of before- and after-example images of a transformation, a system that models by analogy produces analogous transformations on arbitrary new images. This paper brings the expressive power of modelling by analogy to meshes.

To avoid the difficulty of specifying fully 3D example meshes, we use Curve Analogies to produce changes in meshes. We apply analogies to families of curves on an object's surface, and use the filtered curves to drive a transformation of the object. We demonstrate a range of filters, from simple local feature elimination/addition, to more general frequency enhancement filters.

We present techniques for accelerated texture synthesis from example images. The key idea of our approach is to divide the task into two phases: analysis, and synthesis. During the analysis phase, we generate a jump map. Using the jump map, the synthesis phase is capable of synthesizing texture similar to the analyzed example at interactive rates. We describe two such synthesis phase algorithms: one for creating images, and one for directly texturing manifold surfaces. We produce texture images at rates comparable to the fastest alternative algorithms, and produce textured surfaces an order of magnitude faster than current alternative approaches. We further develop a new, faster patch-based algorithm for image synthesis which improves the quality of our results on ordered textures. We show how controls used for specifying texture synthesis on surfaces may be used on images as well, allowing interesting new image-based effects, and highlight modelling applications enabled by the speed of our approach.

We present several powerful new techniques for similarity-based modelling of surfaces using geodesic fans, a new framework for local surface comparison. Similarity-based surface modelling provides intelligent surface manipulation by simultaneously applying a modification to all similar areas of the surface. We demonstrate similarity-based painting, deformation, and filtering of surfaces, and show how to vary our similarity measure to encompass geometry, textures, or other arbitrary signals. The basis for our system, geodesic fans are neighbourhoods uniformly sampled in the geodesic polar coordinates of a point on a surface. We show how geodesic fans offer fast approximate alignment and comparison of surface neighbourhoods using simple spoke reordering. As geodesic fans offer a a structurally equivalent definition of neighbourhoods everywhere on a surface, they are amenable to standard acceleration techniques and are well-suited to extending image domain methods for modelling by example to surfaces.

We introduce a new method for fast texture synthesis on surfaces from examples. We generalize the image-based jump map texture synthesis algorithm, which partitions the task of texture synthesis into a slower analysis phase and a fast synthesis phase, by developing a new synthesis phase which works directly on arbitrary surfaces. Our method is one to two orders of magnitude faster than existing techniques, and does not generate any new texture images, enabling interactive applications for reasonably-sized meshes. This capability would be useful in many areas, including the texturing of dynamically-generated surfaces, interactive modelling applications, and rapid prototyping workflows.

Our method remains simple to implement, assigning an offset in texture space to each edge of the mesh, followed by a walk over the mesh vertices to assign texture coordinates. A final step ensures each triangle receives consistent texture coordinates at its corners, and if available, texture blending can be used to improve the quality of results.

While texture synthesis has been well-studied in recent years, real-time techniques remain elusive. To help facilitate real-time texture synthesis, we divide the task of texture synthesis into two phases: a relatively slow analysis phase, and a real-time synthesis phase. Any particular texture need only be analyzed once, and then an unlimited amount of texture may be synthesized in real-time. Our analysis phase generates a jump map, which stores for each input pixel a set of matching input pixels (jumps). Texture synthesis proceeds in real-time as a random walk through the jump map. Each new pixel is synthesized by extending the patch of input texture from which one of its neighbours was copied. Occasionally, a jump is taken through the jump map to begin a new patch. Despite the method’s extreme simplicity, its speed and output quality compares favourably with recent patch-based algorithms.

We introduce the permission grid, a spatial occupancy grid which can be used to guide almost any standard polygonal surface simplification algorithm into generating an approximation with a guaranteed geometric error bound. In particular, all points on the approximation are guaranteed to be within some user-specified distance from the original surface. Such bounds are notably absent from many current simplification methods, and are becoming increasingly important for applications in scientific computing and adaptive level of detail control. Conceptually simple, the permission grid defines a volume in which the approximation must lie, and does not permit the underlying simplification algorithm to generate approximations outside the volume.

The permission grid makes three important, practical improvements over current error-bounded simplification methods. First, it works on arbitrary triangular models, handling all manners of mesh degeneracies gracefully. Further, the error tolerance may be easily expanded as simplification proceeds, allowing the construction of an error-bounded level of detail hierarchy with vertex correspondences among all levels of detail. And finally, the permission grid has a representation complexity independent of the size of the input model, and a small running time overhead, making it more practical and efficient than current methods with similar guarantees.