{"ID":2879851,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.15529","arxiv_id":"2508.15529","title":"ExtraGS: Geometric-Aware Trajectory Extrapolation with Uncertainty-Guided Generative Priors","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2508.15529","url_pdf":"https://arxiv.org/pdf/2508.15529v2","authors":"[\"Kaiyuan Tan\",\"Yingying Shen\",\"Haohui Zhu\",\"Zhiwei Zhan\",\"Shan Zhao\",\"Mingfei Tu\",\"Hongcheng Luo\",\"Haiyang Sun\",\"Bing Wang\",\"Guang Chen\",\"Hangjun Ye\"]","published":"2025-08-21T13:03:01Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}