{"ID":2849574,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.23205","arxiv_id":"2510.23205","title":"VR-Drive: Viewpoint-Robust End-to-End Driving with Feed-Forward 3D Gaussian Splatting","abstract":"End-to-end autonomous driving (E2E-AD) has emerged as a promising paradigm that unifies perception, prediction, and planning into a holistic, data-driven framework. However, achieving robustness to varying camera viewpoints, a common real-world challenge due to diverse vehicle configurations, remains an open problem. In this work, we propose VR-Drive, a novel E2E-AD framework that addresses viewpoint generalization by jointly learning 3D scene reconstruction as an auxiliary task to enable planning-aware view synthesis. Unlike prior scene-specific synthesis approaches, VR-Drive adopts a feed-forward inference strategy that supports online training-time augmentation from sparse views without additional annotations. To further improve viewpoint consistency, we introduce a viewpoint-mixed memory bank that facilitates temporal interaction across multiple viewpoints and a viewpoint-consistent distillation strategy that transfers knowledge from original to synthesized views. Trained in a fully end-to-end manner, VR-Drive effectively mitigates synthesis-induced noise and improves planning under viewpoint shifts. In addition, we release a new benchmark dataset to evaluate E2E-AD performance under novel camera viewpoints, enabling comprehensive analysis. Our results demonstrate that VR-Drive is a scalable and robust solution for the real-world deployment of end-to-end autonomous driving systems.","short_abstract":"End-to-end autonomous driving (E2E-AD) has emerged as a promising paradigm that unifies perception, prediction, and planning into a holistic, data-driven framework. However, achieving robustness to varying camera viewpoints, a common real-world challenge due to diverse vehicle configurations, remains an open problem. I...","url_abs":"https://arxiv.org/abs/2510.23205","url_pdf":"https://arxiv.org/pdf/2510.23205v1","authors":"[\"Hoonhee Cho\",\"Jae-Young Kang\",\"Giwon Lee\",\"Hyemin Yang\",\"Heejun Park\",\"Seokwoo Jung\",\"Kuk-Jin Yoon\"]","published":"2025-10-27T10:49:39Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}