Xiaobai Chen will present his research seminar/general exam on Tuesday May 19 at 2PM in Room 402. The members of his committee are: Tom Funkhouser, advisor, Szymon Rusinkiewicz, and Fei-Fei Li. Everyone is invited to attend his talk, and those faculty wishing to remain for the oral exam following are welcome to do so. His abstract and reading list follow below. -------------------------------- Abstract Automatic segmentation of 3D surface meshes into functional parts is a fundamental problem in computer graphics. While many algorithms have been developed over the last several years, there has been little work on the quantitative evaluation of how well they perform. In this project, we built a benchmark for quantitative evaluation of mesh segmentation algorithms. The benchmark comprises of 4,300 manual segmentations for 380 surface meshes of 19 different object categories. It also provides software for analyzing 11 geometric properties of segmentations and producing 4 quantitative metrics for comparison of segmentations. With the benchmark, we further investigate segmentation consistency within the same object category as well the planar reflection symmetry of segmentations. Our results suggest that people are remarkable consistent in the way that they segment most 3D surface meshes, that no one automatic segmentation algorithm is better than the others for all types of objects, and that algorithms based on non-local shape features seem to produce segmentations that most closely resemble ones made by humans. Reading List [Paper] [1] MARTIN, D., FOWLKES, C., TAL, D., AND MALIK, J. 2001. A database of human segmented natural images and its application to evaluating segmentation algorithms 936 and measuring ecological statistics. In in Proc. 8th Intl Conf. Computer Vision, 416�423. [2] UNNIKRISHNAN, R., PANTOFARU, C., AND HEBERT, M. 2005. A measure for objective evaluation of image segmentation algorithms. In Proceedings of the 2005 IEEE Conference on Computer Vision and Pattern Recognition (CVPR �05), Workshop on Empirical Evaluation Methods in Computer Vision, vol. 3, 34 �981 41. [3] HUANG, Q., AND DOM, B. 1995. Quantitative methods of evaluating image segmentation. In ICIP �95: Proceedings of the 1995 International Conference on Image Processing (Vol. 3)-Volume 3, IEEE Computer Society, Washington, DC, USA, 3053. [4] ATTENE, M., KATZ, S., MORTARA, M., PATANE, G., SPAGNUOLO, M., AND TAL, A. 2006. Mesh segmentation - a comparative study. In SMI �06: Proceedings of the IEEE International Conference on Shape Modeling and Applications 2006, IEEE Computer Society, Washington, DC, USA, 7. [5] GOLOVINSKIY, A., AND FUNKHOUSER, T. 2008. Randomized cuts for 3D mesh analysis. ACM Transactions on Graphics (Proc. SIGGRAPH ASIA) 27, 5 (Dec.). [6] KATZ, S., LEIFMAN, G., AND TAL, A. 2005. Mesh segmentation using feature point and core extraction. The Visual Computer 21, 8-10, 649�658. [7] ATTENE, M., FALCIDIENO, B., AND SPAGNUOLO, M. 2006. Hierarchical mesh segmentation based on fitting primitives. Vis. Comput. 22, 3, 181�193. [8] SHAPIRA, L., SHAMIR, A., AND COHEN-OR, D. 2008. Consistent mesh partitioning and skeletonisation using the shape diameter function. Vis. Comput. 24, 4, 249�259. [9] LAI, Y.-K., HU, S.-M., MARTIN, R. R., AND ROSIN, P. L. 2008. Fast mesh segmentation using random walks. In Symposium on Solid and Physical Modeling, 183�191. [10] HOFFMAN, D. D., AND SINGH, M. 1997. Salience of visual parts. Cognition 63, 29�78. [11] SHAMIR, A. 2008. A survey on mesh segmentation techniques. Computer Graphics Forum 28, 6, 1539�1556. [Textbook] Computer Graphics with OpenGL, Third Edition, Donald Hearn and M. Pauline Baker, Prentice Hall, 2004 ISBN: 0-13-015390-7.