用几何感知生成先验，提升自动驾驶场景外推的逼真度与一致性
ExtraGS: Geometric-Aware Trajectory Extrapolation with Uncertainty-Guided Generative Priors
- 提出RSG和FFG混合高斯表示，增强道路与远距离物体建模
- 自监督不确定性估计仅在伪影区域融合生成先验，避免过平滑
- 多数据集验证有效提升外推视图的真实感与几何一致性
从记录的驾驶日志中合成外推视图对自动驾驶场景仿真至关重要，但依然具有挑战性。现有方法利用生成先验作为伪真值，常导致几何不一致和渲染过平滑。为此，我们提出ExtraGS框架，整合几何与生成先验。核心是基于混合高斯-有符号距离函数（SDF）设计的新型道路表面高斯（RSG）表示，以及使用可学习缩放因子高效处理远距离物体的远场高斯（FFG）。此外，我们构建了基于球谐函数的自监督不确定性估计框架，仅在出现外推伪影区域选择性融合生成先验。在多个数据集、多种多摄像头配置及不同生成先验下的大量实验表明，ExtraGS显著提升了外推视图的真实感与几何一致性，同时保持原轨迹的高保真度。
原文摘要 · Abstract (English)
Synthesizing extrapolated views from recorded driving logs is critical for simulating driving scenes for autonomous driving vehicles, yet it remains a challenging task. Recent methods leverage generative priors as pseudo ground truth, but often lead to poor geometric consistency and over-smoothed renderings. To address these limitations, we propose ExtraGS, a holistic framework for trajectory extrapolation that integrates both geometric and generative priors. At the core of ExtraGS is a novel Road Surface Gaussian(RSG) representation based on a hybrid Gaussian-Signed Distance Function (SDF) design, and Far Field Gaussians (FFG) that use learnable scaling factors to efficiently handle distant objects. Furthermore, we develop a self-supervised uncertainty estimation framework based on spherical harmonics that enables selective integration of generative priors only where extrapolation artifacts occur. Extensive experiments on multiple datasets, diverse multi-camera setups, and various generative priors demonstrate that ExtraGS significantly enhances the realism and geometric consistency of extrapolated views, while preserving high fidelity along the original trajectory.
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。