-
SRINet: Learning Strictly Rotation-Invariant Representations for Point Cloud Classification and Segmentation
Point cloud analysis has drawn broader attentions due to its increasing ...
read it
-
Spatial Transformer for 3D Points
Point cloud is an efficient representation of 3D visual data, and enable...
read it
-
A Self Contour-based Rotation and Translation-Invariant Transformation for Point Clouds Recognition
Recently, several direct processing point cloud models have achieved sta...
read it
-
An "augmentation-free" rotation invariant classification scheme on point-cloud and its application to neuroimaging
Recent years have witnessed the emergence and increasing popularity of 3...
read it
-
Effective Rotation-invariant Point CNN with Spherical Harmonics kernels
We present a novel rotation invariant architecture operating directly on...
read it
-
Multiple instance dense connected convolution neural network for aerial image scene classification
With the development of deep learning, many state-of-the-art natural ima...
read it
-
PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors
We present PPF-FoldNet for unsupervised learning of 3D local descriptors...
read it
IEEE Signal Processing Letters
Deep neural networks have achieved great progress in 3D scene understanding. However, recent methods mainly focused on objects with canonical orientations in contrast with random postures in reality. In this letter, we propose a hierarchical neural network, named Local Frame Network (LFNet), based on the local rotation invariant coordinate frame for robust point cloud analysis. The local point patches in different orientated objects are transformed into an identical distribution based on this coordinate frame, and the transformed coordinates are taken as input features to eliminate the influence of rotations at the input level. Meanwhile, a discrete convolution operator is defined in the constructed coordinate frame to extract rotation invariant features from local patches, which can further remove the influence of rotations at the convolution level. Moreover, a Spatial Feature Encoder (SFE) module is utilized to perceive the spatial structure of the local region. Mathematical analysis and experimental results on two public datasets demonstrate that the proposed method can eliminate the influence of rotations without data augmentation and outperforms other state-of-theart methods.
READ FULL TEXT
Comments
There are no comments yet.