Adaptive Graph Convolution for Point Cloud Analysis
This addresses a limitation in point cloud analysis for applications like 3D vision, though it is incremental as it builds on existing graph convolution methods.
The paper tackles the problem of poor distinctive feature learning in 3D point cloud convolution by proposing Adaptive Graph Convolution (AdaptConv), which generates adaptive kernels based on learned features, and it outperforms state-of-the-art methods on classification and segmentation benchmarks.
Convolution on 3D point clouds that generalized from 2D grid-like domains is widely researched yet far from perfect. The standard convolution characterises feature correspondences indistinguishably among 3D points, presenting an intrinsic limitation of poor distinctive feature learning. In this paper, we propose Adaptive Graph Convolution (AdaptConv) which generates adaptive kernels for points according to their dynamically learned features. Compared with using a fixed/isotropic kernel, AdaptConv improves the flexibility of point cloud convolutions, effectively and precisely capturing the diverse relations between points from different semantic parts. Unlike popular attentional weight schemes, the proposed AdaptConv implements the adaptiveness inside the convolution operation instead of simply assigning different weights to the neighboring points. Extensive qualitative and quantitative evaluations show that our method outperforms state-of-the-art point cloud classification and segmentation approaches on several benchmark datasets. Our code is available at https://github.com/hrzhou2/AdaptConv-master.