Co-Fix3D: Enhancing 3D Object Detection with Collaborative Refinement

TL;DR

Co-Fix3D introduces a novel 3D object detection framework that enhances feature refinement using wavelet transforms and attention mechanisms, significantly improving detection accuracy in complex driving environments.

Contribution

The paper presents Co-Fix3D, a new detection framework that employs local and global enhancement modules with multi-head attention to improve 3D detection performance.

Findings

Achieves 69.4% mAP on nuScenes LiDAR benchmark

Attains 73.5% NDS on nuScenes LiDAR benchmark

Outperforms previous methods in complex road scenarios

Abstract

3D object detection in driving scenarios faces the challenge of complex road environments, which can lead to the loss or incompleteness of key features, thereby affecting perception performance. To address this issue, we propose an advanced detection framework called Co-Fix3D. Co-Fix3D integrates Local and Global Enhancement (LGE) modules to refine Bird's Eye View (BEV) features. The LGE module uses Discrete Wavelet Transform (DWT) for pixel-level local optimization and incorporates an attention mechanism for global optimization. To handle varying detection difficulties, we adopt multi-head LGE modules, enabling each module to focus on targets with different levels of detection complexity, thus further enhancing overall perception capability. Experimental results show that on the nuScenes dataset's LiDAR benchmark, Co-Fix3D achieves 69.4\% mAP and 73.5\% NDS, while on the multimodal benchmark, it achieves 72.3\% mAP and 74.7\% NDS. The source code is publicly available at \href{https://github.com/rubbish001/Co-Fix3d}{https://github.com/rubbish001/Co-Fix3d}.