MORPHOS可生成带拓扑变化的4D动态3D资产，支持多种表示形式。
MORPHOS: Autoregressive 4D Generation with Temporal Structured Latents
- 用时序结构潜在变量统一建模4D几何与外观，实现跨表示生成。
- 在多个基准上达到最优外观表现，长视频生成保持时间一致性。
- 适合需要动态3D内容生成的研究者和开发者，尤其关注拓扑演化场景。
我们提出MORPHOS，一种新型自回归框架，能从视频中生成跨多种表示形式（包括网格、3D高斯和辐射场）的动态3D资产。现有方法通常局限于单一表示形式，难以建模拓扑变化，或在长视频中无法保持时间一致性。为此，我们引入时序结构潜在变量（T-SLAT），这是一种联合编码时空几何与外观的统一4D表示。基于T-SLAT，MORPHOS通过因果注意力自回归生成动态3D资产，每帧依赖历史信息以确保时间一致性并处理拓扑演变。我们还提出时序结构增强策略，缓解自回归生成中的误差累积问题。MORPHOS在多个基准上实现了领先的外观性能，几何表现具有竞争力，展现出跨表示的强大泛化能力及长时程生成的鲁棒性。
原文摘要 · Abstract (English)
We present MORPHOS, a novel autoregressive framework that generates dynamic 3D assets from videos across diverse representations, including meshes, 3D Gaussians, and radiance fields. Existing methods are typically limited to a single representation, struggle to model topological changes, or fail to maintain temporal consistency over long videos. To address these limitations, we introduce the Temporal Structured Latents (T-SLAT), a unified 4D representation that jointly encodes geometry and appearance along the temporal dimension. Leveraging T-SLAT, MORPHOS autoregressively generates dynamic 3D assets via causal attention, conditioning each frame on its preceding history to ensure temporal consistency while handling evolving topologies. We also propose a temporal-structural augmentation to mitigate error accumulation in autoregressive generation. MORPHOS achieves state-of-the-art performance in appearance and competitive results in geometry across multiple benchmarks, demonstrating superior generalization across various representations and robustness in long-horizon 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。