UniM$^2$AE: Multi-modal Masked Autoencoders with Unified 3D Representation for 3D Perception in Autonomous Driving

• URL: http://arxiv.org/abs/2308.10421v3
• Date: Fri, 23 Aug 2024 04:51:18 GMT
• Title: UniM$^2$AE: Multi-modal Masked Autoencoders with Unified 3D Representation for 3D Perception in Autonomous Driving
• Authors: Jian Zou, Tianyu Huang, Guanglei Yang, Zhenhua Guo, Tao Luo, Chun-Mei Feng, Wangmeng Zuo,
• Abstract summary: Masked Autoencoders (MAE) play a pivotal role in learning potent representations, delivering outstanding results across various 3D perception tasks. This research delves into multi-modal Masked Autoencoders tailored for a unified representation space in autonomous driving. To intricately marry the semantics inherent in images with the geometric intricacies of LiDAR point clouds, we propose UniM$2$AE.
• Score: 47.590099762244535
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Masked Autoencoders (MAE) play a pivotal role in learning potent representations, delivering outstanding results across various 3D perception tasks essential for autonomous driving. In real-world driving scenarios, it's commonplace to deploy multiple sensors for comprehensive environment perception. Despite integrating multi-modal features from these sensors can produce rich and powerful features, there is a noticeable challenge in MAE methods addressing this integration due to the substantial disparity between the different modalities. This research delves into multi-modal Masked Autoencoders tailored for a unified representation space in autonomous driving, aiming to pioneer a more efficient fusion of two distinct modalities. To intricately marry the semantics inherent in images with the geometric intricacies of LiDAR point clouds, we propose UniM$^2$AE. This model stands as a potent yet straightforward, multi-modal self-supervised pre-training framework, mainly consisting of two designs. First, it projects the features from both modalities into a cohesive 3D volume space to intricately marry the bird's eye view (BEV) with the height dimension. The extension allows for a precise representation of objects and reduces information loss when aligning multi-modal features. Second, the Multi-modal 3D Interactive Module (MMIM) is invoked to facilitate the efficient inter-modal interaction during the interaction process. Extensive experiments conducted on the nuScenes Dataset attest to the efficacy of UniM$^2$AE, indicating enhancements in 3D object detection and BEV map segmentation by 1.2\% NDS and 6.5\% mIoU, respectively. The code is available at https://github.com/hollow-503/UniM2AE.

Related papers

• Progressive Multi-Modal Fusion for Robust 3D Object Detection [12.048303829428452]
  Existing methods perform sensor fusion in a single view by projecting features from both modalities either in Bird's Eye View (BEV) or Perspective View (PV) We propose ProFusion3D, a progressive fusion framework that combines features in both BEV and PV at both intermediate and object query levels. Our architecture hierarchically fuses local and global features, enhancing the robustness of 3D object detection.
  arXiv  Detail & Related papers  (2024-10-09T22:57:47Z)
• DeepInteraction++: Multi-Modality Interaction for Autonomous Driving [80.8837864849534]
  We introduce a novel modality interaction strategy that allows individual per-modality representations to be learned and maintained throughout. DeepInteraction++ is a multi-modal interaction framework characterized by a multi-modal representational interaction encoder and a multi-modal predictive interaction decoder. Experiments demonstrate the superior performance of the proposed framework on both 3D object detection and end-to-end autonomous driving tasks.
  arXiv  Detail & Related papers  (2024-08-09T14:04:21Z)
• UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation [113.35352122662752]
  We present an efficient multi-modal backbone for outdoor 3D perception named UniTR. UniTR processes a variety of modalities with unified modeling and shared parameters. UniTR is also a fundamentally task-agnostic backbone that naturally supports different 3D perception tasks.
  arXiv  Detail & Related papers  (2023-08-15T12:13:44Z)
• SimDistill: Simulated Multi-modal Distillation for BEV 3D Object Detection [56.24700754048067]
  Multi-view camera-based 3D object detection has become popular due to its low cost, but accurately inferring 3D geometry solely from camera data remains challenging. We propose a Simulated multi-modal Distillation (SimDistill) method by carefully crafting the model architecture and distillation strategy. Our SimDistill can learn better feature representations for 3D object detection while maintaining a cost-effective camera-only deployment.
  arXiv  Detail & Related papers  (2023-03-29T16:08:59Z)
• MSeg3D: Multi-modal 3D Semantic Segmentation for Autonomous Driving [15.36416000750147]
  We propose a multi-modal 3D semantic segmentation model (MSeg3D) with joint intra-modal feature extraction and inter-modal feature fusion. MSeg3D still shows robustness and improves the LiDAR-only baseline.
  arXiv  Detail & Related papers  (2023-03-15T13:13:03Z)
• PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection [26.03582038710992]
  Masked Autoencoders learn strong visual representations and achieve state-of-the-art results in several independent modalities. In this work, we focus on point cloud and RGB image data, two modalities that are often presented together in the real world. We propose PiMAE, a self-supervised pre-training framework that promotes 3D and 2D interaction through three aspects.
  arXiv  Detail & Related papers  (2023-03-14T17:58:03Z)
• Joint-MAE: 2D-3D Joint Masked Autoencoders for 3D Point Cloud Pre-training [65.75399500494343]
  Masked Autoencoders (MAE) have shown promising performance in self-supervised learning for 2D and 3D computer vision. We propose Joint-MAE, a 2D-3D joint MAE framework for self-supervised 3D point cloud pre-training.
  arXiv  Detail & Related papers  (2023-02-27T17:56:18Z)
• HUM3DIL: Semi-supervised Multi-modal 3D Human Pose Estimation for Autonomous Driving [95.42203932627102]
  3D human pose estimation is an emerging technology, which can enable the autonomous vehicle to perceive and understand the subtle and complex behaviors of pedestrians. Our method efficiently makes use of these complementary signals, in a semi-supervised fashion and outperforms existing methods with a large margin. Specifically, we embed LiDAR points into pixel-aligned multi-modal features, which we pass through a sequence of Transformer refinement stages.
  arXiv  Detail & Related papers  (2022-12-15T11:15:14Z)
• AutoAlignV2: Deformable Feature Aggregation for Dynamic Multi-Modal 3D Object Detection [17.526914782562528]
  We propose AutoAlignV2, a faster and stronger multi-modal 3D detection framework, built on top of AutoAlign. Our best model reaches 72.4 NDS on nuScenes test leaderboard, achieving new state-of-the-art results.
  arXiv  Detail & Related papers  (2022-07-21T06:17:23Z)

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.