Flex-Convolution - Million-Scale Point-Cloud Learning Beyond Grid-Worlds

By Fabian Groh, Patrick Wieschollek, Hendrik P. A. Lensch. 2018

123 citations recorded by the source corpus.

Traditional convolution layers are specifically designed to exploit the natural data representation of images -- a fixed and regular grid. However, unstructured data like 3D point clouds containing irregular neighborhoods constantly breaks the grid-based data assumption. Therefore applying best-practices and design choices from 2D-image learning methods towards processing point clouds are not readily possible. In this work, we introduce a natural generalization flex-convolution of the conventional convolution layer along with an efficient GPU implementation. We demonstrate competitive performance on rather small benchmark sets using fewer parameters and lower memory consumption and obtain significant improvements on a million-scale real-world dataset. Ours is the first which allows to efficiently process 7 million points concurrently.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline (2021, unknown): “…& Komodakis, 2017; Zaheer et al., 2017; Klokov & Lempitsky, 2017; Xu et al., 2018; Atzmon et al., 2018; Wang et al., 2018a; Li et al., 2018a; Groh et al., 2018; Ben-Shabat et al., 2018; Xie et al., 2018; Li et al., 2018b; Liu et al., 2019a; Thomas et al., 2019; Komarichev et al., 2019; Liu…”
Intrinsic-Extrinsic Convolution and Pooling for Learning on 3D Protein Structures (2021, methodology): “While we state our operation as an unstructured convolution as done in 3D point cloud learning (Hermosilla et al., 2018; Groh et al., 2018; Wu et al., 2019; Xiong et al., 2019; Thomas et al., 2019), it can also be understood in a message passing framework (Kipf & Welling, 2017) where hidden states…”
KPConv: Flexible and Deformable Convolution for Point Clouds (2019, background): “Flex-convolution [10] uses linear functions to model its kernel, which could limit its representative power.”
Monte Carlo convolution for learning on non-uniformly sampled point clouds (2018, methodology): “Most of the existing methods are based on convolving the k nearest neighbors (using a hierarchical structure or not) [Groh et al. 2018; Klokov and Lempitsky 2017; Li et al. 2018; Shen et al. 2017; Wang et al. 2018; Xu et al. 2018].”
SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences (2019, methodology): “To overcome the limitations of the voxel-based representation, such as the exploding memory consumption when the resolution of the voxel grid increases, more recent approaches either upsample voxel-predictions [53] using a CRF or use different representations, like more efficient spatial subdivision”
Low-latency automotive vision with event cameras (2024, unknown): “78).”