Explore the LiDAR-Camera Dynamic Adjustment Fusion for 3D Object Detection
This work addresses the challenge of modality gaps in LiDAR-camera fusion for autonomous driving, presenting an incremental improvement in fusion techniques.
The paper tackles the problem of heterogeneous sensor fusion for 3D object detection in autonomous driving by introducing a dynamic adjustment technology to align modal distributions and learn effective representations, achieving competitive performance on the nuScenes dataset.
Camera and LiDAR serve as informative sensors for accurate and robust autonomous driving systems. However, these sensors often exhibit heterogeneous natures, resulting in distributional modality gaps that present significant challenges for fusion. To address this, a robust fusion technique is crucial, particularly for enhancing 3D object detection. In this paper, we introduce a dynamic adjustment technology aimed at aligning modal distributions and learning effective modality representations to enhance the fusion process. Specifically, we propose a triphase domain aligning module. This module adjusts the feature distributions from both the camera and LiDAR, bringing them closer to the ground truth domain and minimizing differences. Additionally, we explore improved representation acquisition methods for dynamic fusion, which includes modal interaction and specialty enhancement. Finally, an adaptive learning technique that merges the semantics and geometry information for dynamical instance optimization. Extensive experiments in the nuScenes dataset present competitive performance with state-of-the-art approaches. Our code will be released in the future.