Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

SpiralNet++: A Fast and Highly Efficient Mesh Convolution Operator

About

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.

Shunwang Gong, Lei Chen, Michael Bronstein, Stefanos Zafeiriou• 2019

Related benchmarks

TaskDatasetResultRank
AD diagnosisADNI (test)
Bacc70.3
16
3D Shape ReconstructionUHM12k (test)
Mean Euclidean Distance0.1153
6
3D Shape ReconstructionUHM12k +expr. (test)
Mean Euclidean Distance12.58
6
3D Shape ReconstructionHandy (test)
Mean Euclidean Distance (mm/100)26.72
6
FTD diagnosisNIFD (val)
Balanced Accuracy88.5
5
FTD diagnosisNIFD (test)
Balanced Accuracy79.5
5
AD diagnosisADNI (val)
Bacc73.3
5
Showing 7 of 7 rows

Other info

Follow for update