中文标题#
ExtraGS：具有不確定性引導生成先驗的幾何感知軌跡外推
英文标题#
ExtraGS: Geometric-Aware Trajectory Extrapolation with Uncertainty-Guided Generative Priors
中文摘要#
從記錄的駕駛日誌中合成外推視圖對於模擬自動駕駛車輛的駕駛場景至關重要，但仍然是一個具有挑戰性的任務。 最近的方法利用生成先驗作為偽真實數據，但通常會導致幾何一致性較差和渲染過於平滑。 為了解決這些限制，我們提出了 ExtraGS，這是一個整合幾何和生成先驗的整體軌跡外推框架。 ExtraGS 的核心是一種基於混合高斯 - 符號距離函數（SDF）設計的新道路表面高斯（RSG）表示，以及使用可學習縮放因子來高效處理遠處物體的遠場高斯（FFG）。 此外，我們開發了一個基於球面諧波的自監督不確定性估計框架，該框架僅在出現外推伪影時選擇性地集成生成先驗。 在多個數據集、多樣化的多攝像頭設置和各種生成先驗上的廣泛實驗表明，ExtraGS 顯著提高了外推視圖的真實感和幾何一致性，同時保留了原始軌跡上的高保真度。
英文摘要#
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.
文章页面#
PDF 获取#
抖音掃碼查看更多精彩內容