InsFusion: 重新思考用于3D目标检测的实例级激光雷达-相机融合
InsFusion: Rethink Instance-level LiDAR-Camera Fusion for 3D Object Detection
AI总结：
针对多模态3D目标检测中特征处理时噪声误差累积的问题，提出InsFusion方法，通过从原始与融合特征提取候选框查询原始特征并结合注意力机制，在nuScenes数据集上兼容先进基线且实现最优性能。
摘要：
基于多视角相机和激光雷达的三维目标检测是自动驾驶和智能交通的关键组件。然而，在基础特征提取、透视变换和特征融合过程中，噪声和误差会逐渐累积。为解决该问题，我们提出InsFusion，它可从原始特征和融合特征中提取候选框，并利用这些候选框查询原始特征，从而减轻累积误差的影响。此外，通过在原始特征上引入注意力机制，进一步缓解累积误差的影响。在nuScenes数据集上的实验表明，InsFusion与多种先进基线方法兼容，并在3D目标检测任务中实现了新的最先进性能。
英文摘要：
Three-dimensional Object Detection from multi-view cameras and LiDAR is a crucial component for autonomous driving and smart transportation. However, in the process of basic feature extraction, perspective transformation, and feature fusion, noise and error will gradually accumulate. To address this issue, we propose InsFusion, which can extract proposals from both raw and fused features and utilizes these proposals to query the raw features, thereby mitigating the impact of accumulated errors. Additionally, by incorporating attention mechanisms applied to the raw features, it thereby mitigates the impact of accumulated errors. Experiments on the nuScenes dataset demonstrate that InsFusion is compatible with various advanced baseline methods and delivers new state-of-the-art performance for 3D object detection.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
