InfinityDrive:突破驾驶世界模型的时间限制
InfinityDrive: Breaking Time Limits in Driving World Models
AI总结:
本文提出 InfinityDrive 驾驶世界模型,通过时空联合建模、扩展时序训练及记忆机制,实现超过2分钟、1500帧以上的高分辨率一致驾驶视频生成。
摘要:
自动驾驶系统在复杂场景中表现吃力,原因在于难以获取对安全导航至关重要的多样化、大规模且分布外的驾驶数据。世界模型为应对这一挑战提供了有前景的解决方案;然而,当前驾驶世界模型受限于较短的时间窗口和有限的场景多样性。为弥合这一差距,我们提出 InfinityDrive,这是首个具备出色泛化能力的驾驶世界模型,能够生成分钟级视频,并在高保真度、一致性和多样性方面达到最先进性能。InfinityDrive 引入高效的时空联合建模模块,并配合扩展时间训练策略,可生成具有一致空间与时间连贯性的高分辨率(576×1024)视频。通过结合记忆注入与保留机制以及自适应记忆曲线损失以最小化累积误差,该模型实现了持续超过1500帧(超过2分钟)的一致性视频生成。在多个数据集上的综合实验验证了 InfinityDrive 生成复杂多样场景的能力,突显其作为面向自动驾驶不断演进需求而构建的下一代驾驶世界模型的潜力。我们的项目主页:https://metadrivescape.github.io/papers_project/InfinityDrive/page.html
英文摘要:
Autonomous driving systems struggle with complex scenarios due to limited access to diverse, extensive, and out-of-distribution driving data which are critical for safe navigation. World models offer a promising solution to this challenge; however, current driving world models are constrained by short time windows and limited scenario diversity. To bridge this gap, we introduce InfinityDrive, the first driving world model with exceptional generalization capabilities, delivering state-of-the-art performance in high fidelity, consistency, and diversity with minute-scale video generation. InfinityDrive introduces an efficient spatio-temporal co-modeling module paired with an extended temporal training strategy, enabling high-resolution (576$\times$1024) video generation with consistent spatial and temporal coherence. By incorporating memory injection and retention mechanisms alongside an adaptive memory curve loss to minimize cumulative errors, achieving consistent video generation lasting over 1500 frames (more than 2 minutes). Comprehensive experiments in multiple datasets validate InfinityDrive's ability to generate complex and varied scenarios, highlighting its potential as a next-generation driving world model built for the evolving demands of autonomous driving. Our project homepage: https://metadrivescape.github.io/papers_project/InfinityDrive/page.html
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。