ExtraGS: Geometric-Aware Trajectory Extrapolation with Uncertainty-Guided Generative Priors
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914001633411072 |
|---|---|
| author | Tan, Kaiyuan Shen, Yingying Zhu, Haohui Zhan, Zhiwei Zhao, Shan Tu, Mingfei Luo, Hongcheng Sun, Haiyang Wang, Bing Chen, Guang Ye, Hangjun |
| author_facet | Tan, Kaiyuan Shen, Yingying Zhu, Haohui Zhan, Zhiwei Zhao, Shan Tu, Mingfei Luo, Hongcheng Sun, Haiyang Wang, Bing Chen, Guang Ye, Hangjun |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_15529 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ExtraGS: Geometric-Aware Trajectory Extrapolation with Uncertainty-Guided Generative Priors Tan, Kaiyuan Shen, Yingying Zhu, Haohui Zhan, Zhiwei Zhao, Shan Tu, Mingfei Luo, Hongcheng Sun, Haiyang Wang, Bing Chen, Guang Ye, Hangjun Computer Vision and Pattern Recognition 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. |
| title | ExtraGS: Geometric-Aware Trajectory Extrapolation with Uncertainty-Guided Generative Priors |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.15529 |