FGU3R: Fine-Grained Fusion via Unified 3D Representation for Multimodal 3D Object Detection

TL;DR

This paper introduces FGU3R, a multimodal 3D object detection framework that uses a unified 3D representation and fine-grained fusion to improve detection accuracy in autonomous driving scenarios.

Contribution

The paper proposes a novel framework with PRConv for feature extraction and CAAF for adaptive fusion, addressing dimension mismatch issues in multimodal 3D detection.

Findings

Improved detection accuracy on KITTI and nuScenes datasets.

Effective fusion of 3D points and 2D pixels.

Enhanced feature interaction and aggregation.

Abstract

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.