arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.01784cs.CVcs.AI
收藏

打包并强化你的记忆:长时长且一致性的视频生成

Pack and Force Your Memory: Long-form and Consistent Video Generation

ShanghaiTech University(上海科技大学);Tencent Hunyuan(腾讯文言);Nanjing University(南京大学)

Xiaofei Wu, Guozhen Zhang, Zhiyong Xu, Yuan Zhou, Qinglin Lu, Xuming He

AI总结:

针对长视频生成的长程依赖捕捉与误差累积难题,提出可学习上下文检索机制MemoryPack和单步近似策略Direct Forcing,提升生成一致性与可靠性,推进自回归视频模型实用化。

摘要:

长视频生成面临双重挑战:模型必须捕捉长程依赖关系,同时防止自回归解码中固有的误差累积。为应对这些挑战,我们提出两项贡献。首先,针对动态上下文建模,我们提出MemoryPack(记忆打包),这是一种可学习的上下文检索机制,利用文本和图像信息作为全局引导,联合建模短期与长期依赖关系,实现分钟级的时间一致性。该设计可随视频长度灵活扩展,保持计算效率,并维持线性复杂度。其次,为缓解误差累积,我们引入Direct Forcing(直接强制),这是一种高效的单步近似策略,可提升训练与推理的一致性,从而减少推理过程中的误差传播。MemoryPack与Direct Forcing相结合,显著增强了长视频生成的上下文一致性与可靠性,提升了自回归视频模型的实际可用性。

英文摘要:

Long-form video generation presents a dual challenge: models must capture long-range dependencies while preventing the error accumulation inherent in autoregressive decoding. To address these challenges, we make two contributions. First, for dynamic context modeling, we propose MemoryPack, a learnable context-retrieval mechanism that leverages both textual and image information as global guidance to jointly model short- and long-term dependencies, achieving minute-level temporal consistency. This design scales gracefully with video length, preserves computational efficiency, and maintains linear complexity. Second, to mitigate error accumulation, we introduce Direct Forcing, an efficient single-step approximating strategy that improves training-inference alignment and thereby curtails error propagation during inference. Together, MemoryPack and Direct Forcing substantially enhance the context consistency and reliability of long-form video generation, advancing the practical usability of autoregressive video models.

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。

↑