# 3D Point Cloud Feature Explanations Using Gradient-Based Methods

arXiv: https://arxiv.org/abs/2006.05548 · HTML: https://mlsanity.com/paper/2006.05548/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jun 2020.

## Built on by (most cited first, 14 of 14)

- [Surrogate Model-Based Explainability Methods for Point Cloud NNs](https://mlsanity.com/paper/2107.13459/) (2021)
- [Simulating the Real World: A Unified Survey of Multimodal Generative Models](https://mlsanity.com/paper/2503.04641/) (2025)
- [OccAM's Laser: Occlusion-based Attribution Maps for 3D Object Detectors on LiDAR Data](https://mlsanity.com/paper/2204.06577/) (2022)
- [Learning-based 3D Reconstruction in Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2503.14537/) (2025)
- [Visualizing Global Explanations of Point Cloud DNNs](https://mlsanity.com/paper/2203.09505/) (2022)
- [Explainability-Aware One Point Attack for Point Cloud Neural Networks](https://mlsanity.com/paper/2110.04158/) (2021)
- [Explainability of Point Cloud Neural Networks Using SMILE: Statistical Model-Agnostic Interpretability with Local Explanations](https://mlsanity.com/paper/2410.15374/) (2024)
- [One Wave To Explain Them All: A Unifying Perspective On Feature Attribution](https://mlsanity.com/paper/2410.01482/) (2024)
- [Robustifying Point Cloud Networks by Refocusing](https://mlsanity.com/paper/2308.05525/) (2023)
- [FFAM: Feature Factorization Activation Map for Explanation of 3D Detectors](https://mlsanity.com/paper/2405.12601/) (2024)
- [Interpreting Hidden Semantics in the Intermediate Layers of 3D Point Cloud Classification Neural Network](https://mlsanity.com/paper/2303.06652/) (2023)
- [DAM: Diffusion Activation Maximization for 3D Global Explanations](https://mlsanity.com/paper/2401.14938/) (2024)
- [Flow AM: Generating Point Cloud Global Explanations by Latent Alignment](https://mlsanity.com/paper/2404.18760/) (2024)
- [Explainable LiDAR 3D Point Cloud Segmentation and Clustering for Detecting Airplane-Generated Wind Turbulence](https://mlsanity.com/paper/2503.00518/) (2025)

## Abstract (arXiv)

Explainability is an important factor to drive user trust in the use of neural networks for tasks with material impact. However, most of the work done in this area focuses on image analysis and does not take into account 3D data. We extend the saliency methods that have been shown to work on image data to deal with 3D data. We analyse the features in point clouds and voxel spaces and show that edges and corners in 3D data are deemed as important features while planar surfaces are deemed less important. The approach is model-agnostic and can provide useful information about learnt features. Driven by the insight that 3D data is inherently sparse, we visualise the features learnt by a voxel-based classification network and show that these features are also sparse and can be pruned relatively easily, leading to more efficient neural networks. Our results show that the Voxception-ResNet model can be pruned down to 5% of its parameters with negligible loss in accuracy.