LidarAugment: Searching for Scalable 3D LiDAR Data Augmentations

TL;DR

LidarAugment introduces a scalable, search-based data augmentation strategy for 3D LiDAR object detection, reducing hyperparameters and improving performance across multiple models, achieving state-of-the-art results on the Waymo dataset.

Contribution

The paper proposes LidarAugment, a simplified and effective search-based data augmentation method that adapts to different 3D detection models and significantly enhances their performance.

Findings

LidarAugment reduces hyperparameters from 20+ to 2.

It consistently improves various 3D detection models.

Achieves 74.8 mAPH on Waymo Open Dataset, a new state-of-the-art.

Abstract

Data augmentations are important in training high-performance 3D object detectors for point clouds. Despite recent efforts on designing new data augmentations, perhaps surprisingly, most state-of-the-art 3D detectors only use a few simple data augmentations. In particular, different from 2D image data augmentations, 3D data augmentations need to account for different representations of input data and require being customized for different models, which introduces significant overhead. In this paper, we resort to a search-based approach, and propose LidarAugment, a practical and effective data augmentation strategy for 3D object detection. Unlike previous approaches where all augmentation policies are tuned in an exponentially large search space, we propose to factorize and align the search space of each data augmentation, which cuts down the 20+ hyperparameters to 2, and significantly reduces the search complexity. We show LidarAugment can be customized for different model architectures with different input representations by a simple 2D grid search, and consistently improve both convolution-based UPillars/StarNet/RSN and transformer-based SWFormer. Furthermore, LidarAugment mitigates overfitting and allows us to scale up 3D detectors to much larger capacity. In particular, by combining with latest 3D detectors, our LidarAugment achieves a new state-of-the-art 74.8 mAPH L2 on Waymo Open Dataset.