Semantics-Guided Multimodal Masked Autoencoder Pretraining for 3D BEV Object Detection

• URL: http://arxiv.org/abs/2605.25262v1
• Date: Sun, 24 May 2026 21:24:11 GMT
• Title: Semantics-Guided Multimodal Masked Autoencoder Pretraining for 3D BEV Object Detection
• Abstract summary: Multimodal masked autoencoders have shown strong potential for learning such representations for downstream 3D BEV object detection.<n>We propose a semantics-guided multimodal masked autoencoder framework that introduces semantic information during pretraining.<n>On BEVFusion 3D object detection, our semantics-guided pretraining strategy improves performance on the nuScenes mini validation set.
• Score: 2.3402617555964382
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Accurate 3D bird's-eye view (BEV) object detection is essential for autonomous driving, and depends strongly on effective multimodal representations from complementary sensors such as cameras and LiDAR. Multimodal masked autoencoders have shown strong potential for learning such representations for downstream 3D BEV object detection. However, existing methods typically apply uniform random masking to camera and LiDAR inputs, treating all regions equally, and learn representations only through masked reconstruction. We propose a semantics-guided multimodal masked autoencoder framework that introduces semantic information during pretraining through two separate components: (i) semantics-guided LiDAR voxel masking, which preserves semantically important LiDAR regions more strongly, and (ii) an auxiliary point-wise LiDAR semantic decoder branch that injects semantic guidance in addition to reconstruction. On BEVFusion 3D object detection, our semantics-guided pretraining strategy improves performance on the nuScenes mini validation set compared to the standard UniM2AE baseline: semantics-guided LiDAR voxel masking yields +1.49% mean Average Precision (mAP) and +1.66% nuScenes Detection Score (NDS), while decoder-side point semantic supervision yields +1.39% mAP and +3.22% NDS over the baseline.

Related papers

• On the Feasibility and Opportunity of Autoregressive 3D Object Detection [60.86546723351944]
  AutoReg3D is an autoregressive 3D detector that casts detection as sequence generation.<n>It is compatible across diverse point-cloud or backbones and attains competitive nuScenes performance without anchors or NMS.
  arXiv  Detail & Related papers  (2026-03-09T05:46:53Z)
• Triple Point Masking [49.39218611030084]
  Existing 3D mask learning methods encounter performance bottlenecks under limited data. We introduce a triple point masking scheme, named TPM, which serves as a scalable framework for pre-training of masked autoencoders. Extensive experiments show that the four baselines equipped with the proposed TPM achieve comprehensive performance improvements on various downstream tasks.
  arXiv  Detail & Related papers  (2024-09-26T05:33:30Z)
• Learning Shared RGB-D Fields: Unified Self-supervised Pre-training for Label-efficient LiDAR-Camera 3D Perception [17.11366229887873]
  We introduce a unified pretraining strategy, NeRF-Supervised Masked Auto (NS-MAE) NS-MAE exploits NeRF's ability to encode both appearance and geometry, enabling efficient masked reconstruction of multi-modal data. Results: NS-MAE outperforms prior SOTA pre-training methods that employ separate strategies for each modality.
  arXiv  Detail & Related papers  (2024-05-28T08:13:49Z)
• VFMM3D: Releasing the Potential of Image by Vision Foundation Model for Monocular 3D Object Detection [80.62052650370416]
  monocular 3D object detection holds significant importance across various applications, including autonomous driving and robotics. In this paper, we present VFMM3D, an innovative framework that leverages the capabilities of Vision Foundation Models (VFMs) to accurately transform single-view images into LiDAR point cloud representations.
  arXiv  Detail & Related papers  (2024-04-15T03:12:12Z)
• ODM3D: Alleviating Foreground Sparsity for Semi-Supervised Monocular 3D Object Detection [15.204935788297226]
  ODM3D framework entails cross-modal knowledge distillation at various levels to inject LiDAR-domain knowledge into a monocular detector during training. By identifying foreground sparsity as the main culprit behind existing methods' suboptimal training, we exploit the precise localisation information embedded in LiDAR points. Our method ranks 1st in both KITTI validation and test benchmarks, significantly surpassing all existing monocular methods, supervised or semi-supervised.
  arXiv  Detail & Related papers  (2023-10-28T07:12:09Z)
• MAELi: Masked Autoencoder for Large-Scale LiDAR Point Clouds [13.426810473131642]
  Masked AutoEncoder for LiDAR point clouds (MAELi) intuitively leverages the sparsity of LiDAR point clouds in both the encoder and decoder during reconstruction. In a novel reconstruction approach, MAELi distinguishes between empty and occluded space. Thereby, without any ground truth whatsoever and trained on single frames only, MAELi obtains an understanding of the underlying 3D scene geometry and semantics.
  arXiv  Detail & Related papers  (2022-12-14T13:10:27Z)
• BEV-MAE: Bird's Eye View Masked Autoencoders for Point Cloud Pre-training in Autonomous Driving Scenarios [51.285561119993105]
  We present BEV-MAE, an efficient masked autoencoder pre-training framework for LiDAR-based 3D object detection in autonomous driving. Specifically, we propose a bird's eye view (BEV) guided masking strategy to guide the 3D encoder learning feature representation. We introduce a learnable point token to maintain a consistent receptive field size of the 3D encoder.
  arXiv  Detail & Related papers  (2022-12-12T08:15:03Z)
• Boosting 3D Object Detection by Simulating Multimodality on Point Clouds [51.87740119160152]
  This paper presents a new approach to boost a single-modality (LiDAR) 3D object detector by teaching it to simulate features and responses that follow a multi-modality (LiDAR-image) detector. The approach needs LiDAR-image data only when training the single-modality detector, and once well-trained, it only needs LiDAR data at inference. Experimental results on the nuScenes dataset show that our approach outperforms all SOTA LiDAR-only 3D detectors.
  arXiv  Detail & Related papers  (2022-06-30T01:44:30Z)
• PillarGrid: Deep Learning-based Cooperative Perception for 3D Object Detection from Onboard-Roadside LiDAR [15.195933965761645]
  We propose textitPillarGrid, a novel cooperative perception method fusing information from multiple 3D LiDARs. PillarGrid consists of four main phases: 1) cooperative preprocessing of point clouds, 2) pillar-wise voxelization and feature extraction, 3) grid-wise deep fusion of features from multiple sensors, and 4) convolutional neural network (CNN)-based augmented 3D object detection. Extensive experimentation shows that PillarGrid outperforms the SOTA single-LiDAR-based 3D object detection methods with respect to both accuracy and range by a large margin.
  arXiv  Detail & Related papers  (2022-03-12T02:28:41Z)
• The Devil is in the Task: Exploiting Reciprocal Appearance-Localization Features for Monocular 3D Object Detection [62.1185839286255]
  Low-cost monocular 3D object detection plays a fundamental role in autonomous driving. We introduce a Dynamic Feature Reflecting Network, named DFR-Net. We rank 1st among all the monocular 3D object detectors in the KITTI test set.
  arXiv  Detail & Related papers  (2021-12-28T07:31:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.