DSAR：用于生成逼真可动画化虚拟化身的布料时序动力学双流自回归建模
DSAR: Dual-Stream Autoregressive Modeling of Temporal Cloth Dynamics for Photorealistic Animatable Avatars
- Nanjing University（南京大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出DSAR双流自回归框架，显式建模布料时序因果结构，解决现有方法布料动力学捕捉不足问题，在多方面性能获显著提升。
AI中文摘要：
从RGB视频创建逼真且时序一致的可动画化人类虚拟化身仍是一项挑战。现有方法难以捕捉逼真的布料动力学，在分布外姿态上会产生过度平滑的外观或严重伪影。这一局限源于一个根本疏漏：现有方法忽略了布料物理固有时序因果性，即当前状态通过时序演化由先前状态产生，而非仅由瞬时骨骼配置决定。若不显式建模该因果结构，网络会学习姿态-外观关联而非运动演化，导致泛化能力差。本文提出一种双流自回归框架，显式建模可观测几何信息与隐式内部状态：几何流传播前一帧的表面位移，状态流将当前特征与从记忆库检索的历史状态融合；运动自适应聚合处理空间变化的动力学，自适应正则化平衡平滑度与灵活性。在具有挑战性的数据集上的实验表明，该方法在渲染质量、时序一致性和对训练分布外运动模式的泛化能力上均有显著提升，验证了双流时序建模可实现逼真的布料动力学。
英文摘要：
Creating photorealistic and temporally coherent animatable human avatars from RGB videos remains challenging. Current methods struggle to capture realistic cloth dynamics, producing over-smoothed appearance or severe artifacts on out-of-distribution poses. This limitation stems from a fundamental oversight: existing approaches neglect the temporal causality inherent in cloth physics, where current states emerge from previous states through temporal evolution rather than instantaneous skeletal configurations alone. Without explicit modeling of this causal structure, networks learn pose-appearance correlations instead of motion evolution, leading to poor generalization. We introduce a dual-stream autoregressive framework that explicitly models both observable geometric information and implicit internal state. The geometric stream propagates surface displacement from the previous frame, while the state stream fuses current features with historical states retrieved from a memory bank. Motion-adaptive aggregation handles spatially-varying dynamics, and adaptive regularization balances smoothness with flexibility. Experiments on challenging datasets demonstrate significant improvements in rendering quality, temporal consistency, and generalization to motion patterns beyond training distributions, validating that dual-stream temporal modeling enables realistic cloth dynamics.
