Metraipolis › archive › dc_9ea19154dfa3
GeoFlow: Efficient Driving Video Generation via Geometry-Aligned Priors — arXiv:2608.12203
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.12203
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T05:49:42.526Z
- SHA-256 of the archived text
b433dc99f4adf29f34a94268b3b9a1ec9f450116f3a085e030938d96718077dc- Stable URL of this page
https://metraipolis.com/documento/dc_9ea19154dfa3
How to cite
GeoFlow: Efficient Driving Video Generation via Geometry-Aligned Priors — arXiv:2608.12203 — arXiv (en), https://arxiv.org/abs/2608.12203 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9ea19154dfa3 (Metraipolis archive dc_9ea19154dfa3, sha256 b433dc99f4adf29f34a94268b3b9a1ec9f450116f3a085e030938d96718077dc)
BibTeX
@misc{dc9ea19154dfa3,
title = {GeoFlow: Efficient Driving Video Generation via Geometry-Aligned Priors — arXiv:2608.12203},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.12203},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9ea19154dfa3; sha256 b433dc99f4adf29f34a94268b3b9a1ec9f450116f3a085e030938d96718077dc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12203. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Generative models like Diffusion Models and Flow Matching have demonstrated remarkable capabilities in synthesizing high-fidelity driving videos, but are severely constrained by high inference latency due to the requirement of extensive sampling steps. We argue that this inefficiency stems from the prevailing reliance on a standard Gaussian source distribution, where consecutive frames are initialized as independent Gaussian noise. This paradigm disregards the rich spatiotemporal correlations inherent in driving videos, compelling the model to regenerate deterministic scene structures existing in previous frames from noise, which is both computationally redundant and prone to geometric inconsistency. To address this problem, we propose GeoFlow, a novel framework designed to achieve efficient driving video generation by harnessing explicit geometric priors. Instead of sampling from standard Gaussian noise, we leverage multi-view geometry and spatially-adaptive noise injection to construct a Geometry-Aligned Prior (GAP) distribution as starting point. This initialization bridges the gap between source distribution and data distribution, yielding a significantly straighter and shorter sampling trajectory. Extensive experiments demonstrate that GeoFlow can achieve remarkable efficiency of both training and inference: merely several hours of fine-tuning on baseline models can significantly boost few-step generation quality, while fully converged training drastically reduces number of inference steps required for state-of-the-art video generation. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-13 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.12203 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T05:42:25.920Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).