Pith. sign in

REVIEW 2 cited by

Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occupancy Autoencoders

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2206.09900 v7 pith:LTUR6WFG submitted 2022-06-20 cs.CV

classification cs.CV
keywords occupancy-maelidarmaskedpointcloudslarge-scaleoccupancydata
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Current perception models in autonomous driving heavily rely on large-scale labelled 3D data, which is both costly and time-consuming to annotate. This work proposes a solution to reduce the dependence on labelled 3D training data by leveraging pre-training on large-scale unlabeled outdoor LiDAR point clouds using masked autoencoders (MAE). While existing masked point autoencoding methods mainly focus on small-scale indoor point clouds or pillar-based large-scale outdoor LiDAR data, our approach introduces a new self-supervised masked occupancy pre-training method called Occupancy-MAE, specifically designed for voxel-based large-scale outdoor LiDAR point clouds. Occupancy-MAE takes advantage of the gradually sparse voxel occupancy structure of outdoor LiDAR point clouds and incorporates a range-aware random masking strategy and a pretext task of occupancy prediction. By randomly masking voxels based on their distance to the LiDAR and predicting the masked occupancy structure of the entire 3D surrounding scene, Occupancy-MAE encourages the extraction of high-level semantic information to reconstruct the masked voxel using only a small number of visible voxels. Extensive experiments demonstrate the effectiveness of Occupancy-MAE across several downstream tasks. For 3D object detection, Occupancy-MAE reduces the labelled data required for car detection on the KITTI dataset by half and improves small object detection by approximately 2% in AP on the Waymo dataset. For 3D semantic segmentation, Occupancy-MAE outperforms training from scratch by around 2% in mIoU. For multi-object tracking, Occupancy-MAE enhances training from scratch by approximately 1% in terms of AMOTA and AMOTP. Codes are publicly available at https://github.com/chaytonmin/Occupancy-MAE.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Point Cloud Understanding via Attention-Driven Contrastive Learning

    cs.CV 2024-11 conditional novelty 6.0 of 10

    By masking high-attention patches and aligning the features of masked and unmasked views, PointACL improves point cloud classification, part segmentation, and few-shot learning over baseline pretraining methods.

  2. VisionPAD: A Vision-Centric Pre-training Paradigm for Autonomous Driving

    cs.CV 2024-11 conditional novelty 6.0 of 10

    VisionPAD uses 3D Gaussian Splatting, self-supervised voxel velocity estimation, and photometric consistency to pre-train vision-centric driving models from images only.

Pith tools