PAI3D: Painting Adaptive Instance-Prior for 3D Object Detection

TL;DR

PAI3D introduces a novel multi-modal fusion framework that leverages instance-level image semantics to significantly enhance 3D object detection accuracy in autonomous driving scenarios.

Contribution

The paper proposes PAI3D, a flexible method that fuses instance-level image semantics with point cloud data to improve 3D detection performance.

Findings

Achieves 71.4 mAP and 74.2 NDS on nuScenes dataset.

Instance-level semantics contribute most to performance gains.

Compatible with various segmentation models and 3D encoders.

Abstract

3D object detection is a critical task in autonomous driving. Recently multi-modal fusion-based 3D object detection methods, which combine the complementary advantages of LiDAR and camera, have shown great performance improvements over mono-modal methods. However, so far, no methods have attempted to utilize the instance-level contextual image semantics to guide the 3D object detection. In this paper, we propose a simple and effective Painting Adaptive Instance-prior for 3D object detection (PAI3D) to fuse instance-level image semantics flexibly with point cloud features. PAI3D is a multi-modal sequential instance-level fusion framework. It first extracts instance-level semantic information from images, the extracted information, including objects categorical label, point-to-object membership and object position, are then used to augment each LiDAR point in the subsequent 3D detection network to guide and improve detection performance. PAI3D outperforms the state-of-the-art with a large margin on the nuScenes dataset, achieving 71.4 in mAP and 74.2 in NDS on the test split. Our comprehensive experiments show that instance-level image semantics contribute the most to the performance gain, and PAI3D works well with any good-quality instance segmentation models and any modern point cloud 3D encoders, making it a strong candidate for deployment on autonomous vehicles.