用上下文压缩技术实现高效长视频生成，保持时序连贯性。
LoViC: Efficient Long Video Generation with Context Compression
- 通过可变压缩率的统一编码器，将视频与文本压缩为潜在表示
- 支持多片段生成、插值等任务，线性调整压缩率提升效率
- 适合需要长时视频生成且注重连贯性的研究与应用
尽管扩散变换器（DiT）在文本到视频生成中取得进展，但其自注意力机制的二次复杂度限制了长视频生成。现有方法如稀疏注意力和时序自回归模型虽缓解部分问题，却常牺牲时序连贯性或可扩展性。我们提出LoViC，一种基于DiT、在百万级开放域视频上训练的框架，通过分段生成实现长视频连续输出。核心是FlexFormer，一种表达能力强的自编码器，能联合压缩视频与文本为统一潜在表示。该设计采用单个查询标记，支持可变长度输入与线性可调压缩率，基于Q-Former架构。同时，通过位置感知机制编码时间上下文，使模型可在统一框架内实现预测、回溯、插值及多片段生成。大量实验验证了方法的有效性与多功能性。
原文摘要 · Abstract (English)
Despite recent advances in diffusion transformers (DiTs) for text-to-video generation, scaling to long-duration content remains challenging due to the quadratic complexity of self-attention. While prior efforts -- such as sparse attention and temporally autoregressive models -- offer partial relief, they often compromise temporal coherence or scalability. We introduce LoViC, a DiT-based framework trained on million-scale open-domain videos, designed to produce long, coherent videos through a segment-wise generation process. At the core of our approach is FlexFormer, an expressive autoencoder that jointly compresses video and text into unified latent representations. It supports variable-length inputs with linearly adjustable compression rates, enabled by a single query token design based on the Q-Former architecture. Additionally, by encoding temporal context through position-aware mechanisms, our model seamlessly supports prediction, retradiction, interpolation, and multi-shot generation within a unified paradigm. Extensive experiments across diverse tasks validate the effectiveness and versatility of our approach.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。