SPE-Net: Boosting Point Cloud Analysis via Rotation Robustness Enhancement

  title={SPE-Net: Boosting Point Cloud Analysis via Rotation Robustness Enhancement},
  author={Zhaofan Qiu and Yehao Li and Yu Wang and Yingwei Pan and Ting Yao and Tao Mei},
. In this paper, we propose a novel deep architecture tailored for 3D point cloud applications, named as SPE-Net. The embedded “Se-lective Position Encoding (SPE)” procedure relies on an attention mechanism that can effectively attend to the underlying rotation condition of the input. Such encoded rotation condition then determines which part of the network parameters to be focused on, and is shown to efficiently help reduce the degree of freedom of the optimization during training. This… 

RotPredictor: Unsupervised Canonical Viewpoint Learning for Point Cloud Classification

This work proposes to rotate the point cloud into a canonical viewpoint for boosting the following downstream target task, e.g., object classification and part segmentation, and is an independent plug and play module, which can be employed by any point-based deep learning framework without extra burden.

A Rotation-Invariant Framework for Deep Point Cloud Analysis

This article introduces a new low-level purely rotation-invariant representation to replace common 3D Cartesian coordinates as the network inputs, and presents a network architecture to embed these representations into features, encoding local relations between points and their neighbors, and the global shape structure.

ClusterNet: Deep Hierarchical Cluster Network With Rigorously Rotation-Invariant Representation for Point Cloud Analysis

This paper introduces a novel point cloud representation that can be mathematically proved rigorously rotation-invariant, i.e., identical point clouds in different orientations are unified as a unique and consistent representation.

SRINet: Learning Strictly Rotation-Invariant Representations for Point Cloud Classification and Segmentation

Point cloud analysis has drawn broader attentions due to its increasing demands in various fields. Despite the impressive performance has been achieved on several databases, researchers neglect the

A Closer Look at Rotation-invariant Deep Point Cloud Analysis

This investigation reveals that the ambiguity problem associated with the PCA-based canonical poses is handled insufficiently in some recent works, and develops a simple pose selector module for disambiguation that presents noticeable enhancement over state-of-the-art approaches on the challenging real-world dataset.

RIConv++: Effective Rotation Invariant Convolutions for 3D Point Clouds Deep Learning

This work proposes a simple yet effective convolution operator that enhances feature distinction by designing powerful rotation invariant features from the local regions, and considers the relationship between the point of interest and its neighbors as well as the internal relationship of the neighbors to largely improve the feature descriptiveness.

Effective Rotation-Invariant Point CNN with Spherical Harmonics Kernels

This work demonstrates how rotation invariance can be injected into a recently proposed point-based PCNN architecture, on all layers of the network, and achieves accurate results on challenging shape analysis tasks, without requiring data-augmentation typically employed by non-invariant approaches.

Deep Positional and Relational Feature Learning for Rotation-Invariant Point Cloud Analysis

A novel deep network for point clouds analysis is proposed by incorporating positional information of points as inputs while yielding rotation-invariance, and experiments show state-of-the-art classification and segmentation performances on benchmark datasets.

SGMNet: Learning Rotation-Invariant Point Cloud Representations via Sorted Gram Matrix

This paper presents a simple but effective local feature representation, called sorted Gram matrix(SGM), which is not only invariant to arbitrary rotations, but also models the pair-wise relationship of all the points in a neighbor-hood, and mathematically proves that the Gram matrix is rotation-invariant and sufficient to model the inherent structure of a point cloud patch.

PVNet: A Joint Convolutional Network of Point Cloud and Multi-View for 3D Shape Recognition

The Point-View Network (PVNet) is proposed, the first framework integrating both the point cloud and the multi-view data towards joint 3D shape recognition, and an embedding attention fusion scheme is proposed that could employ high-level features from the Multi-View data to model the intrinsic correlation and discriminability of different structure features fromThe point cloud data.