MapGS：面向在线建图的可泛化预训练与基于新视角合成的数据增强方法
MapGS: Generalizable Pretraining and Data Augmentation for Online Mapping via Novel View Synthesis
AI总结：
针对自动驾驶在线建图模型跨传感器配置泛化性差的问题，提出基于Gaussian splatting的MapGS框架，通过新视角合成实现数据增强，在nuScenes等数据集上性能提升18%，仅用25%数据即超越SOTA，降低标注成本。
摘要：
在线建图降低了自动驾驶车辆对高清（HD）地图的依赖，显著提升了可扩展性。然而，现有进展往往忽略了跨传感器配置的泛化性，导致模型部署在具有不同相机内参和外参的车辆上时性能下降。随着新视角合成方法的快速发展，我们探究了这类技术可在多大程度上被用于解决传感器配置泛化难题。我们提出了一个全新框架，利用Gaussian splatting（高斯溅射）重建场景并渲染目标传感器配置下的相机图像。目标配置的传感器数据，连同映射到目标配置的标签，被用于训练在线建图模型。我们在nuScenes和Argoverse 2数据集上对所提框架进行了验证，结果表明，通过有效的数据集增强，性能提升了18%，实现了更快的收敛速度与高效训练，且仅使用原始训练数据的25%时性能就超越了当前最优水平。该方法实现了数据复用，减少了对繁琐数据标注工作的需求。项目主页：https://henryzhangzhy.github.io/mapgs。
英文摘要：
Online mapping reduces the reliance of autonomous vehicles on high-definition (HD) maps, significantly enhancing scalability. However, recent advancements often overlook cross-sensor configuration generalization, leading to performance degradation when models are deployed on vehicles with different camera intrinsics and extrinsics. With the rapid evolution of novel view synthesis methods, we investigate the extent to which these techniques can be leveraged to address the sensor configuration generalization challenge. We propose a novel framework leveraging Gaussian splatting to reconstruct scenes and render camera images in target sensor configurations. The target config sensor data, along with labels mapped to the target config, are used to train online mapping models. Our proposed framework on the nuScenes and Argoverse 2 datasets demonstrates a performance improvement of 18% through effective dataset augmentation, achieves faster convergence and efficient training, and exceeds state-of-the-art performance when using only 25% of the original training data. This enables data reuse and reduces the need for laborious data labeling. Project page at https://henryzhangzhy.github.io/mapgs.
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。
