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.

We present a system that lets a designer directly annotate a 3D model with strokes, imparting a personal aesthetic to the non-photorealistic rendering of the object. The artist chooses a “brush ” style, then draws strokes over the model from one or more viewpoints. When the system renders the scene from any new viewpoint, it adapts the number and placement of the strokes appropriately to maintain the original look.

Figure 1: (a) A photo of a car engine (b) Stylized rendering highlighting boundaries between geometric shapes. Notice the four spark plugs and the dip-stick which are now clearly visible (c) Photo of a flower plant (d) Texture de-emphasized rendering. We present a non-photorealistic rendering approach to capture and convey shape features of real-world scenes. We use a camera with multiple flashes that are strategically positioned to cast shadows along depth discontinuities in the scene. The projective-geometric relationship of the camera-flash setup is then exploited to detect depth discontinuities and distinguish them from intensity edges due to material discontinuities. We introduce depiction methods that utilize the detected edge features to generate stylized static and animated images. We can highlight the detected features, suppress unnecessary details or combine features from multiple images. The resulting images more clearly convey the 3D structure of the imaged scenes. We take a very different approach to capturing geometric features of a scene than traditional approaches that require reconstructing a 3D model. This results in a method that is both surprisingly simple and computationally efficient. The entire hardware/software setup can conceivably be packaged into a self-contained device no larger than existing digital cameras.

We describe a way to render stylized silhouettes of animated 3D models with temporal coherence. Coherence is one of the central challenges for non-photorealistic rendering. It is especially difficult for silhouettes, because they may not have obvious correspondences between frames. We demonstrate various coherence effects for stylized silhouettes with a robust working system. Our method runs in real-time for models of moderate complexity, making it suitable for both interactive applications and offline animation.

Specifying parameters of analytic BRDF models is a difficult task as these parameters are often not intuitive for artists and their effect on appearance can be non-uniform. Ideally, a given step in the parameter space should produce a predictable and perceptually-uniform change in the rendered image. Systems that employ psychophysics have produced important advances in this direction; however, the requirement of user studies limits scalability of these approaches. In this work, we propose a new and intuitive method for designing material appearance. First, we define a computational metric between BRDFs that is based on rendered images of a scene under natural illumination.

Actual graphic hardware becomes more and more powerful. Consequently, virtual scenes can be rendered in a very good quality integrating dynamic behavior, real-time shadows, bump mapped surfaces and other photorealistic rendering techniques. On the other hand, non-photorealistic rendering became popular as well, because of its artistic merits. An integration in an AR environment is the logical consequence. In this paper we present an AR framework that uses photorealistic rendering as well as non-photorealistic rendering techniques. The prototypes based on these techniques show the advantages and disadvantages of both technologies in combination with Augmented Reality.

This paper introduces a procedural approach to non-photorealistic line drawing from 3D models. The approach is inspired both by procedural shaders in classical rendering and by the power of procedural modeling. We propose a new image creation model where all operations are controlled procedurally. A view map describing all relevant support lines in the drawing is first created from the 3d model; a number of style modules operate on this map, by procedurally selecting and chaining lines before creating strokes and assigning drawing attributes. Two different levels of user control are provided, ranging from a low-level programming API to a parameterized building-block assembly mechanism. The resulting drawing system allows very flexible control of all elements of drawing style: first, different style modules can be applied to different types of lines in a view; second, stroke attributes are assigned procedurally and can be correlated at will with various scene or view properties. We illustrate the components of our system and show results of its application.

In this paper, we present sketchy-ar-us, a modified, real-time version of the Loose and Sketchy algorithm used to render graphics in an AR environment. The primary challenge was to modify the original algorithm to produce a NPR effect at interactive frame rate. Our algorithm renders moderately complex scenes at multiple frames per second. Equipped with a handheld visor, visitors can see the real environment overlaid with virtual objects with both the real and virtual content rendered in a non-photorealistic style.

The notable amount and variation of current techniques in non-photorealistic rendering (NPR) indicates a level of maturity whereby the categorization of algorithms has become possible. We present a conceptual model for NPR, on which we base a modular system, OPENNPAR, which integrates NPR algorithms into distinct classes. Components in OPENNPAR are modularized and consequently reintegrated for various rendering purposes, allowing many kinds of NPR algorithms to be reproduced, including the integration of 2D and 3D methods. Additionally, the system provides support for a range of users (developers, programmers, designers) according to their respective levels of abstraction, thus being available in multiple contexts. Ultimately, OPENNPAR holds great potential as a tool in the development, augmentation, and creation of NPR effects. 1.

We couple artificial ant and computer graphics techniques to create an approach to Non-Photorealistic Rendering (NPR). A user interactively takes turns with an artificial ant colony to transform a photograph into a stylized picture. In turn with the user specifying its control parameters, members of a colony of artificial ants scan the source image locally, following strong edges or wandering around flat zones, and draw marks on the canvas depending on their discoveries. Among a variety of obtained effects, two are painterly rendering and pencil sketching.