提出首个4D生成加速框架，显著提升动态3D内容生成速度。
Turbo4DGen: Ultra-Fast Acceleration for 4D Generation
- 引入时空缓存与动态注意力剪枝，减少重复计算
- 在两个数据集上实现9.7倍加速且无质量损失
- 适合需要快速生成动态3D场景的研究与应用
4D生成（动态3D内容生成）融合空间、时间与视角维度，用于建模真实动态场景，在世界模型与物理AI中具有基础性作用。然而，通过独特的时空相机运动（SCM）注意力机制保持跨帧与视角的长序列一致性，带来巨大计算与内存开销，常导致显存溢出（OOM）和生成时间过长。为此，我们提出Turbo4DGen，一种基于扩散模型的多视角4D内容生成超快加速框架。该框架引入时空缓存机制，持久复用去噪步骤中的中间注意力；结合动态语义感知注意力剪枝与自适应SCM链跳过调度器，大幅减少冗余的SCM注意力计算。实验表明，Turbo4DGen在ObjaverseDy和Consistent4D数据集上平均实现9.7×加速，且无质量下降。据我们所知，Turbo4DGen是首个专为4D生成设计的加速框架。
原文摘要 · Abstract (English)
4D generation, or dynamic 3D content generation, integrates spatial, temporal, and view dimensions to model realistic dynamic scenes, playing a foundational role in advancing world models and physical AI. However, maintaining long-chain consistency across both frames and viewpoints through the unique spatio-camera-motion (SCM) attention mechanism introduces substantial computational and memory overhead, often leading to out-of-memory (OOM) failures and prohibitive generation times. To address these challenges, we propose Turbo4DGen, an ultra-fast acceleration framework for diffusion-based multi-view 4D content generation. Turbo4DGen introduces a spatiotemporal cache mechanism that persistently reuses intermediate attention across denoising steps, combined with dynamically semantic-aware attention pruning and an adaptive SCM chain bypass scheduler, to drastically reduce redundant SCM attention computation. Our experimental results show that Turbo4DGen achieves an average 9.7$\times$ speedup without quality degradation on the ObjaverseDy and Consistent4D datasets. To the best of our knowledge, Turbo4DGen is the first dedicated acceleration framework for 4D generation.
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。