用新视角合成技术提升自动驾驶地图模型跨传感器泛化能力
MapGS: Generalizable Pretraining and Data Augmentation for Online Mapping via Novel View Synthesis
- 用高斯点阵重建场景并合成目标传感器视角图像
- 在nuScenes和Argoverse 2上提升18%性能，仅用25%数据超主流方法
- 适合需要跨设备部署的自动驾驶在线建图系统
在线建图减少对高精地图的依赖，显著提升可扩展性。但现有方法常忽视跨传感器配置的泛化能力，导致在不同相机内参与外参设备上性能下降。随着新视角合成技术的快速发展，我们研究其在解决传感器配置泛化问题中的潜力。提出一种新框架，利用高斯点阵重建场景并渲染目标传感器配置下的图像，结合映射到目标配置的标签训练在线建图模型。在nuScenes和Argoverse 2数据集上的实验表明，该框架通过有效数据增强实现18%的性能提升，收敛更快，训练更高效，且仅使用原始训练数据的25%即超越当前最优水平。这实现了数据复用，降低了人工标注成本。项目页面：https://henryzhangzhy.github.io/mapgs。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。