SurfaceAug：缩小多模态真实标签采样中的差距
SurfaceAug: Closing the Gap in Multimodal Ground Truth Sampling
AI总结：
针对多模态检测器缺乏强数据增强的问题，本文提出 SurfaceAug 真实标签采样算法，通过联合重采样图像与点云实现双模态目标级变换，并在 KITTI 汽车检测上达到新最优。
摘要：
尽管模型架构和数据增强近期均取得进展，多模态目标检测器仍几乎无法超越仅使用 LiDAR 的同类检测器。这一不足被归因于缺乏足够强大的多模态数据增强。为解决该问题，我们提出 SurfaceAug，这是一种新颖的真实标签采样算法。SurfaceAug 通过同时重采样图像和点云来粘贴目标，从而在两种模态中实现目标级变换。我们通过在 KITTI 上训练一个多模态检测器来评估该算法，并将其性能与先前工作进行比较。实验表明，SurfaceAug 在汽车检测任务上优于现有方法，并为多模态真实标签采样确立了新的最优水平。
英文摘要：
Despite recent advances in both model architectures and data augmentation, multimodal object detectors still barely outperform their LiDAR-only counterparts. This shortcoming has been attributed to a lack of sufficiently powerful multimodal data augmentation. To address this, we present SurfaceAug, a novel ground truth sampling algorithm. SurfaceAug pastes objects by resampling both images and point clouds, enabling object-level transformations in both modalities. We evaluate our algorithm by training a multimodal detector on KITTI and compare its performance to previous works. We show experimentally that SurfaceAug outperforms existing methods on car detection tasks and establishes a new state of the art for multimodal ground truth sampling.
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。
