ContrastAlign: Toward Robust BEV Feature Alignment via Contrastive Learning for Multi-Modal 3D Object Detection

• URL: http://arxiv.org/abs/2405.16873v2
• Date: Wed, 5 Jun 2024 11:59:37 GMT
• Title: ContrastAlign: Toward Robust BEV Feature Alignment via Contrastive Learning for Multi-Modal 3D Object Detection
• Authors: Ziying Song, Feiyang Jia, Hongyu Pan, Yadan Luo, Caiyan Jia, Guoxin Zhang, Lin Liu, Yang Ji, Lei Yang, Li Wang,
• Abstract summary: We propose a novel ContrastAlign approach to enhance the alignment of heterogeneous modalities. Our method achieves state-of-the-art performance, with an mAP of 70.3%, surpassing BEVFusion by 1.8% on the nuScenes validation set.
• Score: 21.05923528672353
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In the field of 3D object detection tasks, fusing heterogeneous features from LiDAR and camera sensors into a unified Bird's Eye View (BEV) representation is a widely adopted paradigm. However, existing methods are often compromised by imprecise sensor calibration, resulting in feature misalignment in LiDAR-camera BEV fusion. Moreover, such inaccuracies result in errors in depth estimation for the camera branch, ultimately causing misalignment between LiDAR and camera BEV features. In this work, we propose a novel ContrastAlign approach that utilizes contrastive learning to enhance the alignment of heterogeneous modalities, thereby improving the robustness of the fusion process. Specifically, our approach includes the L-Instance module, which directly outputs LiDAR instance features within LiDAR BEV features. Then, we introduce the C-Instance module, which predicts camera instance features through RoI (Region of Interest) pooling on the camera BEV features. We propose the InstanceFusion module, which utilizes contrastive learning to generate similar instance features across heterogeneous modalities. We then use graph matching to calculate the similarity between the neighboring camera instance features and the similarity instance features to complete the alignment of instance features. Our method achieves state-of-the-art performance, with an mAP of 70.3%, surpassing BEVFusion by 1.8% on the nuScenes validation set. Importantly, our method outperforms BEVFusion by 7.3% under conditions with misalignment noise.

Related papers

• Distribution Discrepancy and Feature Heterogeneity for Active 3D Object Detection [18.285299184361598]
  LiDAR-based 3D object detection is a critical technology for the development of autonomous driving and robotics. We propose a novel and effective active learning (AL) method called Distribution Discrepancy and Feature Heterogeneity (DDFH) It simultaneously considers geometric features and model embeddings, assessing information from both the instance-level and frame-level perspectives.
  arXiv  Detail & Related papers  (2024-09-09T08:26:11Z)
• GraphBEV: Towards Robust BEV Feature Alignment for Multi-Modal 3D Object Detection [18.21607858133675]
  We propose a robust fusion framework called Graph BEV to integrate LiDAR and camera BEV features. Our framework outperforms BEV Fusion by 8.3% under conditions with misalignment noise.
  arXiv  Detail & Related papers  (2024-03-18T15:00:38Z)
• Cameras as Rays: Pose Estimation via Ray Diffusion [54.098613859015856]
  Estimating camera poses is a fundamental task for 3D reconstruction and remains challenging given sparsely sampled views. We propose a distributed representation of camera pose that treats a camera as a bundle of rays. Our proposed methods, both regression- and diffusion-based, demonstrate state-of-the-art performance on camera pose estimation on CO3D.
  arXiv  Detail & Related papers  (2024-02-22T18:59:56Z)
• Diffusion-Based Particle-DETR for BEV Perception [94.88305708174796]
  Bird-Eye-View (BEV) is one of the most widely-used scene representations for visual perception in Autonomous Vehicles (AVs) Recent diffusion-based methods offer a promising approach to uncertainty modeling for visual perception but fail to effectively detect small objects in the large coverage of the BEV. Here, we address this problem by combining the diffusion paradigm with current state-of-the-art 3D object detectors in BEV.
  arXiv  Detail & Related papers  (2023-12-18T09:52:14Z)
• LiDAR-Camera Panoptic Segmentation via Geometry-Consistent and Semantic-Aware Alignment [63.83894701779067]
  We propose LCPS, the first LiDAR-Camera Panoptic network. In our approach, we conduct LiDAR-Camera fusion in three stages. Our fusion strategy improves about 6.9% PQ performance over the LiDAR-only baseline on NuScenes dataset.
  arXiv  Detail & Related papers  (2023-08-03T10:57:58Z)
• BEV-IO: Enhancing Bird's-Eye-View 3D Detection with Instance Occupancy [58.92659367605442]
  We present BEV-IO, a new 3D detection paradigm to enhance BEV representation with instance occupancy information. We show that BEV-IO can outperform state-of-the-art methods while only adding a negligible increase in parameters and computational overhead.
  arXiv  Detail & Related papers  (2023-05-26T11:16:12Z)
• BEVFusion4D: Learning LiDAR-Camera Fusion Under Bird's-Eye-View via Cross-Modality Guidance and Temporal Aggregation [14.606324706328106]
  We propose a dual-branch framework to generate LiDAR and camera BEV, then perform an adaptive modality fusion. A LiDAR-Guided View Transformer (LGVT) is designed to effectively obtain the camera representation in BEV space. Our framework dubbed BEVFusion4D achieves state-of-the-art results in 3D object detection.
  arXiv  Detail & Related papers  (2023-03-30T02:18:07Z)
• TiG-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry Learning [7.6887888234987125]
  We propose a learning scheme of Target Inner-Geometry from the LiDAR modality into camera-based BEV detectors. TiG-BEV can effectively boost BEVDepth by +2.3% NDS and +2.4% mAP, along with BEVDet by +9.1% NDS and +10.3% mAP on nuScenes val set.
  arXiv  Detail & Related papers  (2022-12-28T17:53:43Z)
• Benchmarking the Robustness of LiDAR-Camera Fusion for 3D Object Detection [58.81316192862618]
  Two critical sensors for 3D perception in autonomous driving are the camera and the LiDAR. fusing these two modalities can significantly boost the performance of 3D perception models. We benchmark the state-of-the-art fusion methods for the first time.
  arXiv  Detail & Related papers  (2022-05-30T09:35:37Z)
• BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation [105.96557764248846]
  We introduce BEVFusion, a generic multi-task multi-sensor fusion framework. It unifies multi-modal features in the shared bird's-eye view representation space. It achieves 1.3% higher mAP and NDS on 3D object detection and 13.6% higher mIoU on BEV map segmentation, with 1.9x lower cost.
  arXiv  Detail & Related papers  (2022-05-26T17:59:35Z)
• AutoAlign: Pixel-Instance Feature Aggregation for Multi-Modal 3D Object Detection [46.03951171790736]
  We propose textitAutoAlign, an automatic feature fusion strategy for 3D object detection. We show that our approach can lead to 2.3 mAP and 7.0 mAP improvements on the KITTI and nuScenes datasets.
  arXiv  Detail & Related papers  (2022-01-17T16:08:57Z)

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.