# 3DTI-Net: Learn Inner Transform Invariant 3D Geometry Features using Dynamic GCN

arXiv: https://arxiv.org/abs/1812.06254 · HTML: https://mlsanity.com/paper/1812.06254/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Dec 2018.

## Built on by (most cited first, 7 of 7)

- [PointCLIP: Point Cloud Understanding by CLIP](https://mlsanity.com/paper/2112.02413/) (2021)
- [A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective](https://mlsanity.com/paper/2209.13232/) (2022)
- [DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds](https://mlsanity.com/paper/2111.08799/) (2021)
- [diffConv: Analyzing Irregular Point Clouds with an Irregular View](https://mlsanity.com/paper/2111.14658/) (2021)
- [Differentiable Convolution Search for Point Cloud Processing](https://mlsanity.com/paper/2108.12856/) (2021)
- [Structure-Aware Multi-Hop Graph Convolution for Graph Neural Networks](https://mlsanity.com/paper/2112.01714/) (2021)
- [Attention-based Graph Convolution Fusing Latent Structures and Multiple Features for Graph Neural Networks](https://mlsanity.com/paper/2303.00944/) (2023)

## Abstract (arXiv)

Deep learning on point clouds has made a lot of progress recently. Many point cloud dedicated deep learning frameworks, such as PointNet and PointNet++, have shown advantages in accuracy and speed comparing to those using traditional 3D convolution algorithms. However, nearly all of these methods face a challenge, since the coordinates of the point cloud are decided by the coordinate system, they cannot handle the problem of 3D transform invariance properly. In this paper, we propose a general framework for point cloud learning. We achieve transform invariance by learning inner 3D geometry feature based on local graph representation, and propose a feature extraction network based on graph convolution network. Through experiments on classification and segmentation tasks, our method achieves state-of-the-art performance in rotated 3D object classification, and achieve competitive performance with the state-of-the-art in classification and segmentation tasks with fixed coordinate value.