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 View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

open-mmlab/mmdetection3d officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to An Empirical Study of Training State-of-the-Art LiDAR Segmentation Models (arXiv:2405.14870; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
AllenPeng0209/deeproute_competition mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection (arXiv:2104.10956; that paper's own run record: 20 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 2 honoured, 1 violated, 11 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
Discover304/MMDetection3D-Eloss mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection (arXiv:2104.10956; that paper's own run record: 20 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 2 honoured, 1 violated, 11 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
bosszhe/vimi mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to VIMI: Vehicle-Infrastructure Multi-view Intermediate Fusion for Camera-based 3D Object... (arXiv:2303.10975; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
jhkim-spa/FVNet_v2 mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection (arXiv:2104.10956; that paper's own run record: 20 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 2 honoured, 1 violated, 11 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
konyul/mmdet3d mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection (arXiv:2104.10956; that paper's own run record: 20 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 2 honoured, 1 violated, 11 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
vision-agh/pointpillars-backbone mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
vision-agh/pointpillars_backbone mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
yhbcode000/MMDetection3D-Eloss mentioned on GitHubpytorchApache-2.0Syntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

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