Escape From Cells: Deep Kd-networks For The Recognition Of 3D Point Cloud Models

Abstract

We present a new deep learning architecture (called Kd-network) that is designed for 3D model recognition tasks and works with unstructured point clouds. The new architecture performs multiplicative transformations and share parameters of these transformations according to the subdivisions of the point clouds imposed onto them by Kd-trees. Unlike the currently dominant convolutional architectures that usually require rasterization on uniform two-dimensional or three-dimensional grids, Kd-networks do not rely on such grids in any way and therefore avoid poor scaling behaviour. In a series of experiments with popular shape recognition benchmarks, Kd-networks demonstrate competitive performance in a number of shape recognition tasks such as shape classification, shape retrieval and shape part segmentation.

Stats

• citations758
• S2 citations—
• github stars0
• HF likes0
• heat score21.60
• arxiv keyklokov2017escape

Related papers

• Deeppoint3d: Learning Discriminative Local Descriptors Using Deep Metric Learning On 3D Point Clouds (2019)9.59
• Pvrnet: Point-view Relation Neural Network For 3D Shape Recognition (2018)13.11
• Lpd-net: 3D Point Cloud Learning For Large-scale Place Recognition And Environment Analysis (2018)18.40
• Unsupervised Detection Of Distinctive Regions On 3D Shapes (2019)7.50
• DH3D: Deep Hierarchical 3D Descriptors For Robust Large-scale 6dof Relocalization (2020)14.76
• Adversarial Autoencoders For Compact Representations Of 3D Point Clouds (2018)14.06
• Pointnetvlad: Deep Point Cloud Based Retrieval For Large-scale Place Recognition (2018)25.45
• KP-RED: Exploiting Semantic Keypoints For Joint 3D Shape Retrieval And Deformation (2024)8.35