看得清晰，忘得深刻：重新审视面向驾驶仿真的微调视频生成器
Seeing Clearly, Forgetting Deeply: Revisiting Fine-Tuned Video Generators for Driving Simulation
AI总结：
本文揭示微调视频生成器用于驾驶仿真时存在视觉保真度提升但空间动态准确性下降的权衡，并提出多样领域回放等持续学习策略可在保持视觉质量的同时保留空间准确性。
摘要：
视频生成领域的最新进展大幅提升了视觉质量和时间连贯性，使这些模型对自动驾驶等应用越来越具有吸引力，尤其是在驾驶仿真和所谓的“世界模型”背景下。本文研究了现有微调视频生成方法在结构化驾驶数据集上的效果，并揭示了一个潜在的权衡：尽管视觉保真度有所提高，但对动态元素建模的空间准确性可能会下降。我们将这种退化归因于视觉质量目标与动态理解目标之间对齐关系的偏移。在时间空间中具有多样场景结构的数据集里，物体或视角以不同方式变化，这些目标往往高度相关。然而，驾驶场景高度规律且重复的特性使得模型可以通过建模主导场景运动模式来提升视觉质量，而不必保留细粒度的动态行为。因此，微调促使模型优先考虑表面层面的真实感，而非动态准确性。为了进一步研究这一现象，我们证明简单的持续学习策略（例如来自多样领域的回放）可以提供一种平衡的替代方案，在保持强大视觉质量的同时保留空间准确性。
英文摘要：
Recent advancements in video generation have substantially improved visual quality and temporal coherence, making these models increasingly appealing for applications such as autonomous driving, particularly in the context of driving simulation and so-called "world models". In this work, we investigate the effects of existing fine-tuning video generation approaches on structured driving datasets and uncover a potential trade-off: although visual fidelity improves, spatial accuracy in modeling dynamic elements may degrade. We attribute this degradation to a shift in the alignment between visual quality and dynamic understanding objectives. In datasets with diverse scene structures within temporal space, where objects or perspective shift in varied ways, these objectives tend to highly correlated. However, the very regular and repetitive nature of driving scenes allows visual quality to improve by modeling dominant scene motion patterns, without necessarily preserving fine-grained dynamic behavior. As a result, fine-tuning encourages the model to prioritize surface-level realism over dynamic accuracy. To further examine this phenomenon, we show that simple continual learning strategies, such as replay from diverse domains, can offer a balanced alternative by preserving spatial accuracy while maintaining strong visual quality.
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。
