In computer graphics, mesh decomposition is a fundamental problem and it can benefit many applications. In this paper, we propose a novel mesh decomposition algorithm using motion information derived from a given animation sequence. The proposed algorithm first use principal component analysis (PCA) to construct a compact representation of a given animation sequence. Next, from this representation, we derive several motion parameters including motion complexity and similarity. Finally, we decompose a given mesh into submeshes using derived motion information and subdivide the triangles along the cutting paths for the smoother borders between the mesh parts. Our experimental results show that this new decomposition scheme can bring the benefit of good compression ratios on animation sequences.

No abstract

Abstract-We describe a low-cost three-dimensional (3-D) virtual colonoscopy system that is a noninvasive technique for examining the entire colon and can assist physicians in detecting polyps inside the colon. Using the helical CT data and proposed techniques, we can three-dimensionally reconstruct and visualize the inner surface of the colon. We generate high resolution of video views of the colon interior structures as if the viewer's eyes were inside the colon. The physicians can virtually navigate inside the colon in two different modes: interactive and automatic navigation, respectively. For automatic navigation, the flythrough path is determined a priori using the 3-D thinning and twopass tracking schemes. The whole colon is spatially subdivided into several cells, and only potentially visible cells are taken into account during rendering. To further improve rendering efficiency, potentially visible cells are rendered at different levels of detail. Additionally, a chain of bounding volume in each cell is used to avoid penetrating through the colon during navigation. In comparison with previous work, the proposed system can efficiently accomplish required preprocessing tasks and afford adequate rendering speeds on a low-cost PC system. Index Terms-Adaptive selection of level of detail, flythrough path, interactive rendering, level-of-detail, potentially visible set, segmentation, virtual colonoscopy.

No abstract

In this paper, we propose a novel vector field, called a camera-sampling field, to represent the sampling density distribution of a pinhole camera. We give the derivation and discuss some essential properties of the camera-sampling field, including flux, divergence, curl, gradient, level surface, and sampling patterns. This vector field reveals camera-sampling concisely and facilitates camera sampling analysis. The usage for this vector field in several computer graphics applications is introduced, such as determining the splat kernel for image-based rendering, texture filtering, mipmap level selection, level transition criteria for LOD, and LDI-construction.