# Deformable Filter Convolution for Point Cloud Reasoning

arXiv: https://arxiv.org/abs/1907.13079 · HTML: https://mlsanity.com/paper/1907.13079/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jul 2019.

## Built on by (most cited first, 4 of 4)

- [Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling](https://mlsanity.com/paper/2107.02389/) (2021)
- [Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator for Vision Applications](https://mlsanity.com/paper/2401.06197/) (2024)
- [big.LITTLE Vision Transformer for Efficient Visual Recognition](https://mlsanity.com/paper/2410.10267/) (2024)
- [Dynamic Prototype Adaptation with Distillation for Few-shot Point Cloud Segmentation](https://mlsanity.com/paper/2401.16051/) (2024)

## Abstract (arXiv)

Point clouds are the native output of many real-world 3D sensors. To borrow the success of 2D convolutional network architectures, a majority of popular 3D perception models voxelize the points, which can result in a loss of local geometric details that cannot be recovered. In this paper, we propose a novel learnable convolution layer for processing 3D point cloud data directly. Instead of discretizing points into fixed voxels, we deform our learnable 3D filters to match with the point cloud shape. We propose to combine voxelized backbone networks with our deformable filter layer at 1) the network input stream and 2) the output prediction layers to enhance point level reasoning. We obtain state-of-the-art results on LiDAR semantic segmentation and producing a significant gain in performance on LiDAR object detection.