Stable volumetric features in deformable shapes

详细信息	查看全文 | 推荐本文 |

• 作者：R. Litman^a ; ^{roeelitm@post.tau.ac.il} ; A.M. Bronstein^a ; M.M. Bronstein^b
• 关键词：Deformable shapes ; Feature detection ; Diffusion geometry ; Component tree ; Level sets ; MSER feature descriptor ; Non-rigid shapes ; Maximally stable components ; Intrinsic geometry
• 刊名：Computers and Graphics
• 出版年：2012
• 期刊代码：36_00978493
• 类别：cp
• 出版时间：August, 2012
• 卷：36
• 期：5
• 页码：569-576
• 文件大小：817 K

摘要

Region feature detectors and descriptors have become a successful and popular alternative to point descriptors in image analysis due to their high robustness and repeatability, leading to a significant interest in the shape analysis community in finding analogous approaches in the 3D world. Recent works have successfully extended the maximally stable extremal region (MSER) detection algorithm to surfaces. In many applications, however, a volumetric shape model is more appropriate, and modeling shape deformations as approximate isometries of the volume of an object, rather than its boundary, better captures natural behavior of non-rigid deformations. In this paper, we formulate a diffusion-geometric framework for volumetric stable component detection and description in deformable shapes. An evaluation of our method on the SHREC'11 feature detection benchmark and SCAPE human body scans shows its potential as a source of high-quality features. Examples demonstrating the drawbacks of surface stable components and the advantage of their volumetric counterparts are also presented.