{"ID":2833012,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.04830","arxiv_id":"2512.04830","title":"FreeGen: Feed-Forward Reconstruction-Generation Co-Training for Free-Viewpoint Driving Scene Synthesis","abstract":"Closed-loop simulation and scalable pre-training for autonomous driving require synthesizing free-viewpoint driving scenes. However, existing datasets and generative pipelines rarely provide consistent off-trajectory observations, limiting large-scale evaluation and training. While recent generative models demonstrate strong visual realism, they struggle to jointly achieve interpolation consistency and extrapolation realism without per-scene optimization. To address this, we propose FreeGen, a feed-forward reconstruction-generation co-training framework for free-viewpoint driving scene synthesis. The reconstruction model provides stable geometric representations to ensure interpolation consistency, while the generation model performs geometry-aware enhancement to improve realism at unseen viewpoints. Through co-training, generative priors are distilled into the reconstruction model to improve off-trajectory rendering, and the refined geometry in turn offers stronger structural guidance for generation. Experiments demonstrate that FreeGen achieves state-of-the-art performance for free-viewpoint driving scene synthesis.","short_abstract":"Closed-loop simulation and scalable pre-training for autonomous driving require synthesizing free-viewpoint driving scenes. However, existing datasets and generative pipelines rarely provide consistent off-trajectory observations, limiting large-scale evaluation and training. While recent generative models demonstrate...","url_abs":"https://arxiv.org/abs/2512.04830","url_pdf":"https://arxiv.org/pdf/2512.04830v1","authors":"[\"Shijie Chen\",\"Peixi Peng\"]","published":"2025-12-04T14:14:21Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}