We present a new technique for the display of high-dynamic-range images, which reduces the contrast while preserving detail. It is based on a two-scale decomposition of the image into a base layer, encoding large-scale variations, and a detail layer. Only the base layer has its contrast reduced, thereby preserving detail. The base layer is obtained using an edge-preserving filter called the bilateral filter. This is a non-linear filter, where the weight of each pixel is computed using a Gaussian in the spatial domain multiplied by an influence function in the intensity domain that decreases the weight of pixels with large intensity differences. We express bilateral filtering in the framework of robust statistics and show how it relates to anisotropic diffusion. We then accelerate bilateral filtering by using a piecewise-linear approximation in the intensity domain and appropriate subsampling. This results in a speed-up of two orders of magnitude. The method is fast and requires no parameter setting.

The linear strain measures that are commonly used in real-time animations of deformable objects yield fast and stable simulations. However, they are not suitable for large deformations. Recently, more realistic results have been achieved in computer graphics by using Green's non-linear strain tensor, but the non-linearity makes the simulation more costly and introduces numerical problems.In this paper, we present a new simulation technique that is stable and fast like linear models, but without the disturbing artifacts that occur with large deformations. As a precomputation step, a linear stiffness matrix is computed for the system. At every time step of the simulation, we compute a tensor field that describes the local rotations of all the vertices in the mesh. This field allows us to compute the elastic forces in a non-rotated reference frame while using the precomputed stiffness matrix. The method can be applied to both finite element models and mass-spring systems. Our approach provides robustness, speed, and a realistic appearance in the simulation of large deformations.

We present an image-based modeling and editing system that takes a single photo as input. We represent a scene as a layered collection of depth images, where each pixel encodes both color and depth. Starting from an input image, we employ a suite of user-assisted techniques, based on a painting metaphor, to assign depths and extract layers. We introduce two specific editing operations. The first, a "clone brushing tool," permits the distortion-free copying of parts of a picture, by using a parameterization optimization technique. The second, a "texture-illuminance decoupling filter," discounts the effect of illumination on uniformly textured areas, by decoupling large-and small-scale features via bilateral filtering. Our system enables editing from different viewpoints, extracting and grouping of image-based objects, and modifying the shape, color, and illumination of these objects.

A A basic L-system. The first rule directs the elongation of existing branches with time. The second rule allocates the creation of new branches from a bud, and the development of new buds on the existing branches.

Figure 1: Our method can automatically adjust the appearance of a foreground region to better match the background of a composite. Given the proposed foreground and background on the left, we show the compositing results of unadjusted cut-and-paste, Adobe Photoshop's Match Color, the method of Lalonde and Efros [2007], and our method. AbstractCompositing is one of the most commonly performed operations in computer graphics. A realistic composite requires adjusting the appearance of the foreground and background so that they appear compatible; unfortunately, this task is challenging and poorly understood. We use statistical and visual perception experiments to study the realism of image composites. First, we evaluate a number of standard 2D image statistical measures, and identify those that are most significant in determining the realism of a composite. Then, we perform a human subjects experiment to determine how the changes in these key statistics influence human judgements of composite realism. Finally, we describe a data-driven algorithm that automatically adjusts these statistical measures in a foreground to make it more compatible with its background in a composite. We show a number of compositing results, and evaluate the performance of both our algorithm and previous work with a human subjects study.