FGFusion: Fine-Grained Lidar-Camera Fusion for 3D Object Detection

TL;DR

FGFusion introduces a novel multi-scale, fine-grained fusion approach for lidar and camera data, effectively preserving detailed information for improved 3D object detection in autonomous driving.

Contribution

The paper presents a dual pathway hierarchy and multi-scale fusion technique that enhances the integration of low-level details from images and point clouds.

Findings

Significant performance improvements on KITTI benchmark.

Effective preservation of low-level details in 3D detection.

Outperforms existing fusion methods in accuracy.

Abstract

Lidars and cameras are critical sensors that provide complementary information for 3D detection in autonomous driving. While most prevalent methods progressively downscale the 3D point clouds and camera images and then fuse the high-level features, the downscaled features inevitably lose low-level detailed information. In this paper, we propose Fine-Grained Lidar-Camera Fusion (FGFusion) that make full use of multi-scale features of image and point cloud and fuse them in a fine-grained way. First, we design a dual pathway hierarchy structure to extract both high-level semantic and low-level detailed features of the image. Second, an auxiliary network is introduced to guide point cloud features to better learn the fine-grained spatial information. Finally, we propose multi-scale fusion (MSF) to fuse the last N feature maps of image and point cloud. Extensive experiments on two popular autonomous driving benchmarks, i.e. KITTI and Waymo, demonstrate the effectiveness of our method.