期刊
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW)
卷 -, 期 -, 页码 4141-4148出版社
IEEE COMPUTER SOC
DOI: 10.1109/ICCVW.2019.00509
关键词
-
类别
资金
- ERC [724228]
- Google Faculty Research Awards
- Amazon AWS Machine Learning Research grant
- Royal Society Wolfson Research Merit award
- EPSRC [EP/S010203/1]
- Google Faculty Award
- European Research Council (ERC) [724228] Funding Source: European Research Council (ERC)
Intrinsic graph convolution operators with differentiable kernel functions play a crucial role in analyzing 3D shape meshes. In this paper, we present a fast and efficient intrinsic mesh convolution operator that does not rely on the intricate design of kernel function. We explicitly formulate the order of aggregating neighboring vertices, instead of learning weights between nodes, and then a fully connected layer follows to fuse local geometric structure information with vertex features. We provide extensive evidence showing that models based on this convolution operator are easier to train, and can efficiently learn invariant shape features. Specifically, we evaluate our method on three different types of tasks of dense shape correspondence, 3D facial expression classification, and 3D shape reconstruction, and show that it significantly outperforms state-of-the-art approaches while being significantly faster, without relying on shape descriptors. Our source code is available on GitHub(1).
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据