# 3D Point Cloud Classification and Segmentation using 3D Modified Fisher Vector Representation for Convolutional Neural Networks

arXiv: https://arxiv.org/abs/1711.08241 · HTML: https://mlsanity.com/paper/1711.08241/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Nov 2017.

## Built on by (most cited first, 8 of 8)

- [AGConv: Adaptive Graph Convolution on 3D Point Clouds](https://mlsanity.com/paper/2206.04665/) (2022)
- [Interpreting Representation Quality of DNNs for 3D Point Cloud Processing](https://mlsanity.com/paper/2111.03549/) (2021)
- [FatNet: A Feature-attentive Network for 3D Point Cloud Processing](https://mlsanity.com/paper/2104.03427/) (2021)
- [Noise Injection-based Regularization for Point Cloud Processing](https://mlsanity.com/paper/2103.15027/) (2021)
- [Privacy-preserving Pedestrian Tracking using Distributed 3D LiDARs](https://mlsanity.com/paper/2303.09915/) (2023)
- [Shrinking unit: a Graph Convolution-Based Unit for CNN-like 3D Point Cloud Feature Extractors](https://mlsanity.com/paper/2209.12770/) (2022)
- [VTPNet for 3D deep learning on point cloud](https://mlsanity.com/paper/2305.06115/) (2023)
- [Global Attention-Guided Dual-Domain Point Cloud Feature Learning for Classification and Segmentation](https://mlsanity.com/paper/2407.08994/) (2024)

## Abstract (arXiv)

The point cloud is gaining prominence as a method for representing 3D shapes, but its irregular format poses a challenge for deep learning methods. The common solution of transforming the data into a 3D voxel grid introduces its own challenges, mainly large memory size. In this paper we propose a novel 3D point cloud representation called 3D Modified Fisher Vectors (3DmFV). Our representation is hybrid as it combines the discrete structure of a grid with continuous generalization of Fisher vectors, in a compact and computationally efficient way. Using the grid enables us to design a new CNN architecture for point cloud classification and part segmentation. In a series of experiments we demonstrate competitive performance or even better than state-of-the-art on challenging benchmark datasets.