Window Normalization: Enhancing Point Cloud Understanding by Unifying Inconsistent Point Densities

5 Dec 2022  ·  Qi Wang, Sheng Shi, Jiahui Li, Wuming Jiang, Xiangde Zhang ·

Downsampling and feature extraction are essential procedures for 3D point cloud understanding. Existing methods are limited by the inconsistent point densities of different parts in the point cloud. In this work, we analyze the limitation of the downsampling stage and propose the pre-abstraction group-wise window-normalization module. In particular, the window-normalization method is leveraged to unify the point densities in different parts. Furthermore, the group-wise strategy is proposed to obtain multi-type features, including texture and spatial information. We also propose the pre-abstraction module to balance local and global features. Extensive experiments show that our module performs better on several tasks. In segmentation tasks on S3DIS (Area 5), the proposed module performs better on small object recognition, and the results have more precise boundaries than others. The recognition of the sofa and the column is improved from 69.2% to 84.4% and from 42.7% to 48.7%, respectively. The benchmarks are improved from 71.7%/77.6%/91.9% (mIoU/mAcc/OA) to 72.2%/78.2%/91.4%. The accuracies of 6-fold cross-validation on S3DIS are 77.6%/85.8%/91.7%. It outperforms the best model PointNeXt-XL (74.9%/83.0%/90.3%) by 2.7% on mIoU and achieves state-of-the-art performance. The code and models are available at https://github.com/DBDXSS/Window-Normalization.git.

PDF Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Semantic Segmentation S3DIS WindowNorm+StratifiedTransformer Mean IoU 77.6 # 6
mAcc 85.8 # 5
oAcc 91.7 # 6
Number of params 8.2M # 45
Params (M) 8.2 # 8
Semantic Segmentation S3DIS WindowNorm+PointTransformer Mean IoU 74.1 # 14
mAcc 82.5 # 14
oAcc 90.2 # 11
Number of params 8.0M # 44
Params (M) 8 # 9
Semantic Segmentation S3DIS Area5 WindowNorm+PointTransformer mIoU 71.4 # 18
oAcc 91.1 # 13
mAcc 77.9 # 14
Number of params N/A # 2
Semantic Segmentation S3DIS Area5 WindowNorm+StratifiedTransformer mIoU 72.2 # 13
oAcc 91.4 # 10
mAcc 78.2 # 8
Number of params N/A # 2

Methods


No methods listed for this paper. Add relevant methods here