Regularization Strategy for Point Cloud via Rigidly Mixed Sample
- URL: http://arxiv.org/abs/2102.01929v1
- Date: Wed, 3 Feb 2021 08:03:59 GMT
- Title: Regularization Strategy for Point Cloud via Rigidly Mixed Sample
- Authors: Dogyoon Lee, Jaeha Lee, Junhyeop Lee, Hyeongmin Lee, Minhyeok Lee,
Sungmin Woo, and Sangyoun Lee
- Abstract summary: This paper proposes a novel data augmentation method for point clouds that generates a virtual mixed sample by replacing part of the sample with shape-preserved subsets from another sample.
Experiments verified that RSMix successfully regularized the deep neural networks with remarkable improvement for shape classification.
- Score: 5.9036709911248835
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Data augmentation is an effective regularization strategy to alleviate the
overfitting, which is an inherent drawback of the deep neural networks.
However, data augmentation is rarely considered for point cloud processing
despite many studies proposing various augmentation methods for image data.
Actually, regularization is essential for point clouds since lack of generality
is more likely to occur in point cloud due to small datasets. This paper
proposes a Rigid Subset Mix (RSMix), a novel data augmentation method for point
clouds that generates a virtual mixed sample by replacing part of the sample
with shape-preserved subsets from another sample. RSMix preserves structural
information of the point cloud sample by extracting subsets from each sample
without deformation using a neighboring function. The neighboring function was
carefully designed considering unique properties of point cloud, unordered
structure and non-grid. Experiments verified that RSMix successfully
regularized the deep neural networks with remarkable improvement for shape
classification. We also analyzed various combinations of data augmentations
including RSMix with single and multi-view evaluations, based on abundant
ablation studies.
Related papers
- Asymmetrical Siamese Network for Point Clouds Normal Estimation [13.826173253686726]
In this paper, we explore the consistency of intrinsic features learned from clean and noisy point clouds using an Asymmetric Siamese Network architecture.
By applying reasonable constraints between features extracted from different branches, we enhance the quality of normal estimation.
We introduce a novel multi-view normal estimation dataset that includes a larger variety of shapes with different noise levels.
arXiv Detail & Related papers (2024-06-14T03:07:23Z) - Learning-Based Biharmonic Augmentation for Point Cloud Classification [79.13962913099378]
Biharmonic Augmentation (BA) is a novel and efficient data augmentation technique.
BA diversifies point cloud data by imposing smooth non-rigid deformations on existing 3D structures.
We present AdvTune, an advanced online augmentation system that integrates adversarial training.
arXiv Detail & Related papers (2023-11-10T14:04:49Z) - AU-PD: An Arbitrary-size and Uniform Downsampling Framework for Point
Clouds [6.786701761788659]
We introduce the AU-PD, a novel task-aware sampling framework that directly downsamples point cloud to any smaller size.
We refine the pre-sampled set to make it task-aware, driven by downstream task losses.
With the attention mechanism and proper training scheme, the framework learns to adaptively refine the pre-sampled set of different sizes.
arXiv Detail & Related papers (2022-11-02T13:37:16Z) - ScoreMix: A Scalable Augmentation Strategy for Training GANs with
Limited Data [93.06336507035486]
Generative Adversarial Networks (GANs) typically suffer from overfitting when limited training data is available.
We present ScoreMix, a novel and scalable data augmentation approach for various image synthesis tasks.
arXiv Detail & Related papers (2022-10-27T02:55:15Z) - BIMS-PU: Bi-Directional and Multi-Scale Point Cloud Upsampling [60.257912103351394]
We develop a new point cloud upsampling pipeline called BIMS-PU.
We decompose the up/downsampling procedure into several up/downsampling sub-steps by breaking the target sampling factor into smaller factors.
We show that our method achieves superior results to state-of-the-art approaches.
arXiv Detail & Related papers (2022-06-25T13:13:37Z) - Self-Supervised Arbitrary-Scale Point Clouds Upsampling via Implicit
Neural Representation [79.60988242843437]
We propose a novel approach that achieves self-supervised and magnification-flexible point clouds upsampling simultaneously.
Experimental results demonstrate that our self-supervised learning based scheme achieves competitive or even better performance than supervised learning based state-of-the-art methods.
arXiv Detail & Related papers (2022-04-18T07:18:25Z) - PointLIE: Locally Invertible Embedding for Point Cloud Sampling and
Recovery [35.353458457283544]
Point Cloud Sampling and Recovery (PCSR) is critical for massive real-time point cloud collection and processing.
We propose a novel Locally Invertible Embedding for point cloud adaptive sampling and recovery (PointLIE)
PointLIE unifies point cloud sampling and upsampling to one single framework through bi-directional learning.
arXiv Detail & Related papers (2021-04-30T05:55:59Z) - OMNet: Learning Overlapping Mask for Partial-to-Partial Point Cloud
Registration [31.108056345511976]
OMNet is a global feature based iterative network for partial-to-partial point cloud registration.
We learn masks in a coarse-to-fine manner to reject non-overlapping regions, which converting the partial-to-partial registration to the registration of the same shapes.
arXiv Detail & Related papers (2021-03-01T11:59:59Z) - PRIN/SPRIN: On Extracting Point-wise Rotation Invariant Features [91.2054994193218]
We propose a point-set learning framework PRIN, focusing on rotation invariant feature extraction in point clouds analysis.
In addition, we extend PRIN to a sparse version called SPRIN, which directly operates on sparse point clouds.
Results show that, on the dataset with randomly rotated point clouds, SPRIN demonstrates better performance than state-of-the-art methods without any data augmentation.
arXiv Detail & Related papers (2021-02-24T06:44:09Z) - SPU-Net: Self-Supervised Point Cloud Upsampling by Coarse-to-Fine
Reconstruction with Self-Projection Optimization [52.20602782690776]
It is expensive and tedious to obtain large scale paired sparse-canned point sets for training from real scanned sparse data.
We propose a self-supervised point cloud upsampling network, named SPU-Net, to capture the inherent upsampling patterns of points lying on the underlying object surface.
We conduct various experiments on both synthetic and real-scanned datasets, and the results demonstrate that we achieve comparable performance to the state-of-the-art supervised methods.
arXiv Detail & Related papers (2020-12-08T14:14:09Z)
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.