In this paper, we propose a novel and effective Multi-Level Fusion network, named as MLF-DET, for high-performance cross-modal 3D object DETection, which integrates both the feature-level fusion and decision-level fusion to fully utilize the information in the image. For the feature-level fusion, we present the Multi-scale Voxel Image fusion (MVI) module, which densely aligns multi-scale voxel features with image features. For the decision-level fusion, we propose the lightweight Feature-cued Confidence Rectification (FCR) module which further exploits image semantics to rectify the confidence of detection candidates. Besides, we design an effective data augmentation strategy termed Occlusion-aware GT Sampling (OGS) to reserve more sampled objects in the training scenes, so as to reduce overfitting. Extensive experiments on the KITTI dataset demonstrate the effectiveness of our method. Notably, on the extremely competitive KITTI car 3D object detection benchmark, our method reaches 82.89% moderate AP and achieves state-of-the-art performance without bells and whistles.

翻译：本文提出了一种新颖且高效的多层级融合网络MLF-DET，用于高性能跨模态三维目标检测。该网络整合了特征级融合与决策级融合，以充分利用图像中的信息。在特征级融合方面，我们提出了多尺度体素-图像融合模块（MVI），该模块将多尺度的体素特征与图像特征进行密集对齐。在决策级融合方面，我们设计了轻量级的特征引导置信度矫正模块（FCR），通过进一步利用图像语义信息来修正检测候选框的置信度。此外，我们还提出了一种名为遮挡感知GT采样（OGS）的有效数据增强策略，在训练场景中保留更多采样目标，从而减少过拟合。在KITTI数据集上的大量实验证明了我们方法的有效性。值得注意的是，在极具竞争力的KITTI汽车三维目标检测基准上，我们的方法无需任何花哨技巧即达到了82.89%的中等平均精度（moderate AP），并实现了最先进的性能。