Advanced Feature Learning on Point Clouds using Multi-resolution
Features and Learnable Pooling
- URL: http://arxiv.org/abs/2205.09962v1
- Date: Fri, 20 May 2022 04:50:10 GMT
- Title: Advanced Feature Learning on Point Clouds using Multi-resolution
Features and Learnable Pooling
- Authors: Kevin Tirta Wijaya, Dong-Hee Paek, Seung-Hyun Kong
- Abstract summary: We propose a novel point cloud feature learning network, PointStack, using multi-resolution feature learning and learnable pooling.
The final aggregated point features can effectively represent both global and local contexts of a point cloud.
- Score: 1.6832237384792461
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: Existing point cloud feature learning networks often incorporate sequences of
sampling, neighborhood grouping, neighborhood-wise feature learning, and
feature aggregation to learn high-semantic point features that represent the
global context of a point cloud. Unfortunately, the compounded loss of
information concerning granularity and non-maximum point features due to
sampling and max pooling could adversely affect the high-semantic point
features from existing networks such that they are insufficient to represent
the local context of a point cloud, which in turn may hinder the network in
distinguishing fine shapes. To cope with this problem, we propose a novel point
cloud feature learning network, PointStack, using multi-resolution feature
learning and learnable pooling (LP). The multi-resolution feature learning is
realized by aggregating point features of various resolutions in the multiple
layers, so that the final point features contain both high-semantic and
high-resolution information. On the other hand, the LP is used as a generalized
pooling function that calculates the weighted sum of multi-resolution point
features through the attention mechanism with learnable queries, in order to
extract all possible information from all available point features.
Consequently, PointStack is capable of extracting high-semantic point features
with minimal loss of information concerning granularity and non-maximum point
features. Therefore, the final aggregated point features can effectively
represent both global and local contexts of a point cloud. In addition, both
the global structure and the local shape details of a point cloud can be well
comprehended by the network head, which enables PointStack to advance the
state-of-the-art of feature learning on point clouds. The codes are available
at https://github.com/kaist-avelab/PointStack.
Related papers
- DCS-Net: Pioneering Leakage-Free Point Cloud Pretraining Framework with
Global Insights [55.051626723729896]
We introduce a novel solution called the Differentiable Center Sampling Network (DCS-Net)
It tackles the information leakage problem by incorporating both global feature reconstruction and local feature reconstruction as non-trivial proxy tasks.
Experimental results demonstrate that our method enhances the expressive capacity of existing point cloud models.
arXiv Detail & Related papers (2024-02-03T08:58:23Z) - Bidirectional Knowledge Reconfiguration for Lightweight Point Cloud
Analysis [74.00441177577295]
Point cloud analysis faces computational system overhead, limiting its application on mobile or edge devices.
This paper explores feature distillation for lightweight point cloud models.
We propose bidirectional knowledge reconfiguration to distill informative contextual knowledge from the teacher to the student.
arXiv Detail & Related papers (2023-10-08T11:32:50Z) - D-Net: Learning for Distinctive Point Clouds by Self-Attentive Point
Searching and Learnable Feature Fusion [48.57170130169045]
We propose D-Net to learn for distinctive point clouds based on a self-attentive point searching and a learnable feature fusion.
To generate a compact feature representation for each distinctive point set, a stacked self-gated convolution is proposed to extract the distinctive features.
The results show that the learned distinction distribution of a point cloud is highly consistent with objects of the same class and different from objects of other classes.
arXiv Detail & Related papers (2023-05-10T02:19:00Z) - Dynamic Local Feature Aggregation for Learning on Point Clouds [15.595200007614274]
We propose a dynamic feature aggregation (DFA) method that can transfer information by constructing local graphs in the feature domain without spatial constraints.
We demonstrate the superiority of our method by conducting extensive experiments on point cloud classification and segmentation tasks.
arXiv Detail & Related papers (2023-01-07T12:18:08Z) - Point cloud completion on structured feature map with feedback network [28.710494879042002]
We propose FSNet, a feature structuring module that can adaptively aggregate point-wise features into a 2D structured feature map.
A 2D convolutional neural network is adopted to decode feature maps from FSNet into a coarse and complete point cloud.
A point cloud upsampling network is used to generate dense point cloud from the partial input and the coarse intermediate output.
arXiv Detail & Related papers (2022-02-17T10:59:40Z) - Self-Sampling for Neural Point Cloud Consolidation [83.31236364265403]
We introduce a novel technique for neural point cloud consolidation which learns from only the input point cloud.
We repeatedly self-sample the input point cloud with global subsets that are used to train a deep neural network.
We demonstrate the ability to consolidate point sets from a variety of shapes, while eliminating outliers and noise.
arXiv Detail & Related papers (2020-08-14T17:16:02Z) - Point Cloud Completion by Learning Shape Priors [74.80746431691938]
shape priors include geometric information in both complete and partial point clouds.
We design a feature alignment strategy to learn the shape prior from complete points, and a coarse to fine strategy to incorporate partial prior in the fine stage.
We achieve state-of-the-art performances on the point cloud completion task.
arXiv Detail & Related papers (2020-08-02T04:00:32Z) - TearingNet: Point Cloud Autoencoder to Learn Topology-Friendly
Representations [20.318695890515613]
We propose an autoencoder, TearingNet, which tackles the challenging task of representing point clouds using a fixed-length descriptor.
Our TearingNet is characterized by a proposed Tearing network module and a Folding network module interacting with each other iteratively.
Experimentation shows the superiority of our proposal in terms of reconstructing point clouds as well as generating more topology-friendly representations than benchmarks.
arXiv Detail & Related papers (2020-06-17T22:42:43Z) - Cascaded Refinement Network for Point Cloud Completion [74.80746431691938]
We propose a cascaded refinement network together with a coarse-to-fine strategy to synthesize the detailed object shapes.
Considering the local details of partial input with the global shape information together, we can preserve the existing details in the incomplete point set.
We also design a patch discriminator that guarantees every local area has the same pattern with the ground truth to learn the complicated point distribution.
arXiv Detail & Related papers (2020-04-07T13:03:29Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.