Papers › Exploring Data Augmentation for Multi-Modality 3D Object Detection

Exploring Data Augmentation for Multi-Modality 3D Object Detection

23 Dec 2020arXiv:2012.12741archive 2025-07-28

Wenwei Zhang, Zhe Wang, Chen Change Loy

It is counter-intuitive that multi-modality methods based on point cloud and images perform only marginally better or sometimes worse than approaches that solely use point cloud. This paper investigates the reason behind this phenomenon. Due to the fact that multi-modality data augmentation must maintain consistency between point cloud and images, recent methods in this field typically use relatively insufficient data augmentation. This shortage makes their performance under expectation. Therefore, we contribute a pipeline, named transformation flow, to bridge the gap between single and multi-modality data augmentation with transformation reversing and replaying. In addition, considering occlusions, a point in different modalities may be occupied by different objects, making augmentations such as cut and paste non-trivial for multi-modality detection. We further present Multi-mOdality Cut and pAste (MoCa), which simultaneously considers occlusion and physical plausibility to maintain the multi-modality consistency. Without using ensemble of detectors, our multi-modality detector achieves new state-of-the-art performance on nuScenes dataset and competitive performance on KITTI 3D benchmark. Our method also wins the best PKL award in the 3rd nuScenes detection challenge. Code and models will be released at https://github.com/open-mmlab/mmdetection3d.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

open-mmlab/mmdetection3d officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
AllenPeng0209/deeproute_competition mentioned on GitHubpytorchApache-2.0 report
Discover304/MMDetection3D-Eloss mentioned on GitHubpytorchApache-2.0 report
bosszhe/vimi mentioned on GitHubpytorchApache-2.0 report
jhkim-spa/FVNet_v2 mentioned on GitHubpytorchApache-2.0 report
konyul/mmdet3d mentioned on GitHubpytorchApache-2.0 report
vision-agh/pointpillars-backbone mentioned on GitHubpytorchApache-2.0 report
vision-agh/pointpillars_backbone mentioned on GitHubpytorchApache-2.0 report
yhbcode000/MMDetection3D-Eloss mentioned on GitHubpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Object DetectionAutonomous DrivingData AugmentationObjectObject Detectionobject-detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections