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

arXiv: https://arxiv.org/abs/2605.25262 · HTML: https://mlsanity.com/paper/2605.25262/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 7 references that are in the map.
- First posted on arXiv 24 May 2026.

## Builds on (most cited first, 6 of 6)

- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation](https://mlsanity.com/paper/2205.13542/) (2022)
- [Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders](https://mlsanity.com/paper/2212.06785/) (2022)
- [SemMAE: Semantic-Guided Masking for Learning Masked Autoencoders](https://mlsanity.com/paper/2206.10207/) (2022)
- [Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occupancy Autoencoders](https://mlsanity.com/paper/2206.09900/) (2022)
- [Masked Autoencoder for Self-Supervised Pre-training on Lidar Point Clouds](https://mlsanity.com/paper/2207.00531/) (2022)

## Abstract (arXiv)

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.