Learning task-specific features for 3D pointcloud graph creation

2022-09-02 · Elías Abad-Rocamora, Javier Ruiz-Hidalgo

Processing 3D pointclouds with Deep Learning methods is not an easy task. A common choice is to do so with Graph Neural Networks, but this framework involves the creation of edges between points, which are explicitly not related between them. Historically, naive and handcrafted methods like k Nearest Neighbors (k-NN) or query ball point over xyz features have been proposed, focusing more attention on improving the network than improving the graph. In this work, we propose a more principled way of creating a graph from a 3D pointcloud. Our method is based on performing k-NN over a transformation of the input 3D pointcloud. This transformation is done by an Multi-Later Perceptron (MLP) with learnable parameters that is optimized through backpropagation jointly with the rest of the network. We also introduce a regularization method based on stress minimization, which allows to control how distant is the learnt graph from our baseline: k-NN over xyz space. This framework is tested on ModelNet40, where graphs generated by our network outperformed the baseline by 0.3 points in overall accuracy.

📄 PDF Abstract BibTeX arXiv:2209.00949

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

k-NN $k$-Nearest Neighbors is a clustering-based algorithm for classification and regression. It is a a type of instance-based learning as it does not attempt to construct a…

Multi-Resolution Graph Neural Network for Large-Scale Pointcloud Segmentation

2020-09-18 · Liuyue Xie, Tomotake Furuhata, Kenji Shimada

In this paper, we propose a multi-resolution deep-learning architecture to semantically segment dense large-scale pointclouds. Dense pointcloud data require a computationally expensive feature encoding process before sem…

GPU Graph Neural Network Segmentation Semantic Segmentation

MuGNet: Multi-Resolution Graph Neural Network for Large-Scale Pointcloud Segmentation

2020-11-16 · Conference on Robot Learning 2020 11 · Liuyue Xie, Tomotake Furuhata, Kenji Shimada

GPU Graph Neural Network Segmentation Semantic Segmentation

SEM-GAT: Explainable Semantic Pose Estimation using Learned Graph Attention

2023-08-07 · Efimia Panagiotaki, Daniele De Martini, Georgi Pramatarov, Matthew Gadd 외

This paper proposes a Graph Neural Network(GNN)-based method for exploiting semantics and local geometry to guide the identification of reliable pointcloud registration candidates. Semantic and morphological features of …

Graph Attention Graph Neural Network Inductive Bias Pose Estimation

Detecting the Anomalies in LiDAR Pointcloud

2023-07-31 · Chiyu Zhang, Ji Han, Yao Zou, Kexin Dong 외

LiDAR sensors play an important role in the perception stack of modern autonomous driving systems. Adverse weather conditions such as rain, fog and dust, as well as some (occasional) LiDAR hardware fault may cause the Li…

Autonomous Driving

EAP-GS: Efficient Augmentation of Pointcloud for 3D Gaussian Splatting in Few-shot Scene Reconstruction

2025-01-01 · CVPR 2025 1 · Dongrui Dai, Yuxiang Xing

3D Gaussian splatting (3DGS) has shown impressive performance in 3D scene reconstruction. However, it suffers from severe degradation when the number of training views is limited, resulting in blur and floaters. Many…

3DGS 3D Scene Reconstruction