Revisiting Point Cloud Simplification: A Learnable Feature Preserving Approach

  title={Revisiting Point Cloud Simplification: A Learnable Feature Preserving Approach},
  author={Rolandos Alexandros Potamias and Giorgos Bouritsas and Stefanos Zafeiriou},
. The recent advances in 3D sensing technology have made possible the capture of point clouds in significantly high resolution. How-ever, increased detail usually comes at the expense of high storage, as well as computational costs in terms of processing and visualization op-erations. Mesh and Point Cloud simplification methods aim to reduce the complexity of 3D models while retaining visual quality and relevant salient features. Traditional simplification techniques usually rely on solving a… 

Neural Mesh Simplification

This work proposes a fast and scalable method that simplifies a given mesh in one-pass, fast, lightweight and differentiable properties that makes it possible to be plugged in every learnable pipeline without introducing a significant overhead.

GraphWalks: Efficient Shape Agnostic Geodesic Shortest Path Estimation

The proposed method provides efficient approximations of the shortest paths and geodesic distances estimations and can be directly plugged into any learnable pipeline as well as customized under any differentiable constraint.

Supplementary Neural Mesh Simplification

The Point Sampler is constructed using three stacked DevConv layers, followed with a ReLU activation, and 64 is selected as a hidden dimension, since the aim for a lightweight and fast model.



Feature Preserving and Uniformity-Controllable Point Cloud Simplification on Graph

A point cloud simplification algorithm, aiming to strike a balance between preserving sharp features and keeping uniform density during resampling, is proposed, leveraging on graph spectral processing to represent irregular point clouds naturally on graphs.

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

This paper designs a novel type of neural network that directly consumes point clouds, which well respects the permutation invariance of points in the input and provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing.

Learning to Sample

It is shown that it is better to learn how to sample, and proposes a deep network to simplify 3D point clouds, termed S-NET, which takes a point cloud and produces a smaller point cloud that is optimized for a particular task.

SampleNet: Differentiable Point Cloud Sampling

  • Itai LangAsaf ManorS. Avidan
  • Computer Science, Environmental Science
    2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2020
This work introduces a novel differentiable relaxation for point cloud sampling that approximates sampled points as a mixture of points in the primary input cloud and outperforms existing non-learned and learned sampling alternatives.

PointASNL: Robust Point Clouds Processing Using Nonlocal Neural Networks With Adaptive Sampling

A novel end-to-end network for robust point clouds processing, named PointASNL, which achieves state-of-the-art robust performance for classification and segmentation tasks on all datasets, and significantly outperforms previous methods on real-world outdoor SemanticKITTI dataset with considerate noise.

LBS Autoencoder: Self-Supervised Fitting of Articulated Meshes to Point Clouds

This work presents LBS-AE; a self-supervised autoencoding algorithm for fitting articulated mesh models to point clouds that achieves performance that is superior to other unsupervised approaches and comparable to methods using supervised examples.

A machine learning framework for full-reference 3D shape quality assessment

This work proposes a novel machine learning-based approach for evaluating the visual quality of 3D static meshes by incorporating crowdsourcing in a machine learning framework for visual quality evaluation and employs crowdsourcing methodology for collecting data of quality evaluations and metric learning for drawing the best parameters that well correlate with the human perception.

PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space

A hierarchical neural network that applies PointNet recursively on a nested partitioning of the input point set and proposes novel set learning layers to adaptively combine features from multiple scales to learn deep point set features efficiently and robustly.

Adaptive simplification of point cloud using k-means clustering

Toronto-3D: A Large-scale Mobile LiDAR Dataset for Semantic Segmentation of Urban Roadways

  • W. TanNannan Qin Jonathan Li
  • Environmental Science, Computer Science
    2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • 2020
Toronto-3D is introduced, a large-scale urban outdoor point cloud dataset acquired by a MLS system in Toronto, Canada for semantic segmentation and the capability of this dataset to train deep learning models effectively is confirmed.