用神经网络模拟人体运动物理，速度比传统方法快10倍
Learned Neural Physics Simulation for Articulated 3D Human Pose Reconstruction
- 构建可循环的神经网络，模拟人体关节与物体接触的动力学
- 在视频重建任务中精度媲美甚至超越传统物理引擎
- 适合需要快速模拟的人体动作重建场景
我们提出一种新型神经网络方法 LARP（Learned Articulated Rigid body Physics），用于建模带接触的人体关节运动动力学。目标是为计算机视觉任务（如视频驱动的人体姿态重建）提供比传统物理模拟器更快、更便捷的替代方案。为此，我们设计了支持循环神经架构的训练流程和模型组件，以准确模拟刚体关节动力学。该神经架构支持关节马达、肢体尺寸可变、肢体间及与物体间的接触等特性，在并行多模拟场景下速度比传统系统快一个数量级。为验证LARP价值，我们将其作为现有视频重建框架中状态领先的经典非可微物理引擎的即插即用替代品，结果表明其3D人体姿态重建精度达到或优于基准。
原文摘要 · Abstract (English)
We propose a novel neural network approach, LARP (Learned Articulated Rigid body Physics), to model the dynamics of articulated human motion with contact. Our goal is to develop a faster and more convenient methodological alternative to traditional physics simulators for use in computer vision tasks such as human motion reconstruction from video. To that end we introduce a training procedure and model components that support the construction of a recurrent neural architecture to accurately simulate articulated rigid body dynamics. Our neural architecture supports features typically found in traditional physics simulators, such as modeling of joint motors, variable dimensions of body parts, contact between body parts and objects, and is an order of magnitude faster than traditional systems when multiple simulations are run in parallel. To demonstrate the value of LARP we use it as a drop-in replacement for a state of the art classical non-differentiable simulator in an existing video-based reconstruction framework and show comparative or better 3D human pose reconstruction accuracy.
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。