FGU3R: Fine-Grained Fusion via Unified 3D Representation for Multimodal 3D Object Detection
This work addresses a specific bottleneck in autonomous driving perception, but it appears incremental as it builds on existing multimodal detection methods.
The paper tackles the problem of dimension mismatches in multimodal 3D object detection for autonomous driving by proposing FGU3R, which uses unified 3D representation and fine-grained fusion, resulting in effective performance as shown in experiments on KITTI and nuScenes datasets.
Multimodal 3D object detection has garnered considerable interest in autonomous driving. However, multimodal detectors suffer from dimension mismatches that derive from fusing 3D points with 2D pixels coarsely, which leads to sub-optimal fusion performance. In this paper, we propose a multimodal framework FGU3R to tackle the issue mentioned above via unified 3D representation and fine-grained fusion, which consists of two important components. First, we propose an efficient feature extractor for raw and pseudo points, termed Pseudo-Raw Convolution (PRConv), which modulates multimodal features synchronously and aggregates the features from different types of points on key points based on multimodal interaction. Second, a Cross-Attention Adaptive Fusion (CAAF) is designed to fuse homogeneous 3D RoI (Region of Interest) features adaptively via a cross-attention variant in a fine-grained manner. Together they make fine-grained fusion on unified 3D representation. The experiments conducted on the KITTI and nuScenes show the effectiveness of our proposed method.