用图注意力网络实时还原人体骨骼朝向，解决动作捕捉数据模糊问题。
Amortized Inverse Kinematics via Graph Attention for Real-Time Human Avatar Animation
- 基于骨骼结构图的注意力机制，单次前向传播恢复全身关节朝向。
- 374K参数，CPU上达650 FPS，比传统方法更快更稳定。
- 适合实时动画、在线交互系统，对噪声和初始姿态鲁棒。
逆运动学（IK）是动画、机器人学和生物力学中的核心操作：给定笛卡尔约束，从已知的运动链结构中恢复关节旋转。在许多实时人体虚拟角色管线中，每帧输入是稀疏的3D关节位置，而动画系统需要关节方向来驱动蒙皮。仅从位置恢复完整朝向存在欠定问题，尤其是骨轴扭转方向不明确；传统IK求解器依赖迭代优化，速度慢且易受噪声影响。本文提出IK-GAT，一种轻量级图注意力网络，通过单次前向传播从3D关节位置重建全身体关节朝向。模型在骨骼父子关系图上进行消息传递，利用运动学结构进行旋转推断。为简化学习，IK-GAT采用以静止姿态骨帧为锚点的骨对齐世界坐标系表示，显式表达扭转轴，并可精确反变换为标准父相对局部旋转。网络使用连续6D旋转表示，训练时采用SO(3)上的测地线损失，可选加入前向运动学一致性正则项。生成的动画就绪局部旋转可直接驱动绑定角色，或转换为类似SMPL的身体姿态参数，适用于实时与在线应用。模型仅含374K参数，在CPU上超过650 FPS，性能优于无需预热的VPoser迭代优化方法，且成本更低，对初始姿态和输入噪声具有鲁棒性。
原文摘要 · Abstract (English)
Inverse kinematics (IK) is a core operation in animation, robotics, and biomechanics: given Cartesian constraints, recover joint rotations under a known kinematic tree. In many real-time human avatar pipelines, the available signal per frame is a sparse set of tracked 3D joint positions, whereas animation systems require joint orientations to drive skinning. Recovering full orientations from positions is underconstrained, most notably because twist about bone axes is ambiguous, and classical IK solvers typically rely on iterative optimization that can be slow and sensitive to noisy inputs. We introduce IK-GAT, a lightweight graph-attention network that reconstructs full-body joint orientations from 3D joint positions in a single forward pass. The model performs message passing over the skeletal parent-child graph to exploit kinematic structure during rotation inference. To simplify learning, IK-GAT predicts rotations in a bone-aligned world-frame representation anchored to rest-pose bone frames. This parameterization makes the twist axis explicit and is exactly invertible to standard parent-relative local rotations given the kinematic tree and rest pose. The network uses a continuous 6D rotation representation and is trained with a geodesic loss on SO(3) together with an optional forward-kinematics consistency regularizer. IK-GAT produces animation-ready local rotations that can directly drive a rigged avatar or be converted to pose parameters of SMPL-like body models for real-time and online applications. With 374K parameters and over 650 FPS on CPU, IK-GAT outperforms VPoser-based per-frame iterative optimization without warm-start at significantly lower cost, and is robust to initial pose and input noise
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。