Acceleration techniques for Rendering in general, and Ray-Casting in particular, have been the subject of much research in Computer Graphics. Most efforts have been focused on new data structures for efficient ray/scene traversal and intersection. In this paper, we propose an acceleration technique that approximates rendering and that is built around a new feature-based clustering approach. The technique starts preprocessing the scene by grouping elements according to their features using a set of channels based on an information theory-based approach. Then, at run-time, a rendering strategy uses that clustering information to reconstruct the final image, by deciding which areas could take advantage of the coherence in the features and thus, could be interpolated; and which areas require more involved calculations. This process starts with a low-resolution render that is iteratively refined up to the desired resolution by reusing previously computed pixels. Our experimental results show a significant speedup of an order of magnitude, depending on the complexity of the per-pixel calculations, the screen size of the objects, and the number of clusters. Rendering quality and speed directly depend on the number of clusters and the number of steps performed during the reconstruction procedure, and both can easily be set by the user. Our findings show that feature-based clustering can significantly impact rendering speed if samples are chosen to enable interpolation of smooth regions. Our technique, thus, accelerates a range of popular and costly techniques, ranging from texture mapping up to complex ambient occlusion, soft and hard shadow calculations, and it can even be used in conjunction with more traditional acceleration methods.

Abstract Ancient cities and castles are ubiquitous cultural heritage structures all over Europe, and countless digital creations (e.g. movies and games) use them for storytelling. However, they got little or no attention in the computer graphics literature. This paper aims to close the gap between historical and geometrical modelling, by presenting a framework that allows the forward and inverse design of ancient city (e.g. castles and walled cities) evolution along history. The main component is an interactive loop that cycles over a number of years simulating the evolution of a city. The user can define events, such as battles, city growth, wall creations or expansions, or any other historical event. Firstly, cities (or castles) and their walls are created, and, later on, expanded to encompass civil or strategic facilities to protect. In our framework, battle simulations are used to detect weaknesses and strengthen them, evolving to accommodate to developments in offensive weaponry. We conducted both forward and inverse design tests on three different scenarios: the city of Carcassone (France), the city of Gerunda (Spain) and the Ciutadella in ancient Barcelona. All the results have been validated by historians who helped fine‐tune the different parameters involved in the simulations.

Abstract This paper presents a new inverse reflector design method using a GPU‐based computation of outgoing light distribution from reflectors. We propose a fast method to obtain the outgoing light distribution of a parametrized reflector, and then compare it with the desired illumination. The new method works completely in the GPU. We trace millions of rays using a hierarchical height‐field representation of the reflector. Multiple reflections are taken into account. The parameters that define the reflector shape are optimized in an iterative procedure in order for the resulting light distribution to be as close as possible to the desired, user‐provided one. We show that our method can calculate reflector lighting at least one order of magnitude faster than previous methods, even with millions of rays, complex geometries and light sources.

Abstract This paper presents a method for compressing measured datasets of the near‐field emission of physical light sources (represented by raysets). We create a mesh on the bounding surface of the light source that stores illumination information. The mesh is augmented with information about directional distribution and energy density. We have developed a new approach to smoothly generate random samples on the illumination distribution represented by the mesh, and to efficiently handle importance sampling of points and directions. We will show that our representation can compress a 10 million particle rayset into a mesh of a few hundred triangles. We also show that the error of this representation is low, even for very close objects.

Reconstructing and rendering trees is a challenging problem due to the geometric complexity involved, and the inherent difficulties of capture. In this paper we propose a volumetric approach to capture and render trees with relatively sparse foliage. Photographs of such trees typically have single pixels containing the blended projection of numerous leaves/branches and background. We show how we estimate opacity values on a recursive grid, based on alphamattes extracted from a small number of calibrated photographs of a tree. This data structure is then used to render billboards attached to the centers of the grid cells. Each billboard is assigned a set of view-dependent textures corresponding to each input view. These textures are generated by approximating coverage masks based on opacity and depth from the camera. Rendering is performed using a view-dependent texturing algorithm. The resulting volumetric tree structure has low polygon count, permitting interactive rendering of realistic 3D trees. We illustrate the implementation of our system on several different real trees, and show that we can insert the resulting model in virtual scenes.

This paper proposes an efficient method for the production of high quality radiosity solutions which uses an a priori knowledge of the dynamic properties of the scene to exploit temporal coherence. The method is based on a two-pass strategy that provides user-control on the final frame quality. In the first pass, it computes a coarse global solution of the radiosities along a time interval and then, in the second pass, it performs a frame-to-frame incremental gathering step using hardware graphic accelerators. Computing cost is thus reduced because the method takes advantage of frame-to-frame coherence by identifying the changes produced by dynamic objects and by decoupling them from computations that remain unchanged. The input data is a dynamic model of the environment through a period of time corresponding to the same camera recording. The method proceeds by incrementally updating two data structures: a space-time hierarchical radiosity solution for a given interval of time and a hierarchical tree of textures representing the space-time final illumination of the visible surfaces. These data structures are computed for a given viewpoint, either static or dynamic. The main contribution of this work is the efficient construction of the texture tree by identifying the changes produced by dynamic objects and by only recomputing these changes.

The paper describes a two pass algorithm capable of computing solutions to the global illumination in general environments (diffuse or glossy surfaces, anisotropically scattering participating media) faster than previous methods, by combining the strengths of finite element and Monte Carlo methods. A quick coarse solution is first computed with a clustered directional hierarchical method. This intermediate solution is used by a Monte Carlo method to accelerate computation of a final accurate solution by importance sampling, by means of link probabilities and adaptive probability density functions. Results from a first implementation of the algorithm for diffuse surfaces are presented.

Finite elements methods for radiosity are aimed at computing global illumination solutions efficiently. However these methods are not suitable for obtaining high quality images due to the lack of error control. Two‐pass methods allow to achieve that level of quality computing illumination at each pixel and thus introducing a high computing overhead. We present a two‐pass method for radiosity that allows to produce high quality images avoiding most of the per‐pixel computations. The method computes a coarse hierarchical radiosity solution and then performs a second pass using current graphics hardware accelerators to generate illumination as high definition textures.

In this paper we present a radiosity algorithm for dynamic scenes with a high level of frame-to-frame coherence. The algorithm is restricted to dynamic environments, where the object's movement is known a priori and the viewpoint is static. Each image is computed as the sum of two images: the base-level image, computed in a pre-process, and the frame-level image computed incrementally at each frame. The computation of the images is based on an importance-driven heuristic approach. The results of the implementation are analysed and discussed. © 1997 John Wiley & Sons, Ltd.