Mesh Segmentation for Parallel Decompression on GPU
- 1.7k Downloads
We present a novel algorithm to partition large 3D meshes for GPU-based decompression. Our formulation focuses on minimizing the replicated vertices between patches, and balancing the numbers of faces of patches for efficient parallel computing. First we generate a topology model of the original mesh and remove vertex positions. Then we assign the centers of patches using geodesic farthest point sampling and cluster the faces according to geodesic distance. After the segmentation we swap boundary faces to fix jagged boundaries and store the boundary vertices for whole-mesh preservation. The decompression of each patch runs on a thread of GPU, we have evaluated its performance on various large benchmarks. In practice, the GPU-based decompression algorithm runs more than 48X faster with that on the CPU.
KeywordsParallel decompression Mesh segmentation Connectivity compression GPU Edgebreaker
Unable to display preview. Download preview PDF.
- 3.Gurung, T., Luffel, M., Lindstrom, P., Rossignac, J.: Lr: compact connectivity representation for triangle meshes. ACM Transactions on Graphics (TOG) 30 (2011)Google Scholar
- 4.Harris, M., Sengupta, S., Owens, J.D.: Parallel prefix sum (scan) with CUDA. In: Nguyen, H. (ed.) GPU Gems 3, ch. 39, pp. 851–876. Addison Wesley (August 2007)Google Scholar
- 9.Rossignac, J.: Edgebreaker: connectivity compression for triangle meshes. IEEE Transactions on Visualization and Computer Graphics 5, 84–115 (1998)Google Scholar
- 10.Yamauchi, H., Lee, S., Lee, Y., Ohtake, Y., Belyaev, A.G., Seidel, H.-P.: Feature sensitive mesh segmentation with mean shift. In: SMI, pp. 238–245 (2005)Google Scholar