论文标题
lcolision：使用学习的非渗透约束，快速生成无碰撞的人姿势
LCollision: Fast Generation of Collision-Free Human Poses using Learned Non-Penetration Constraints
论文作者
论文摘要
我们提出了Lcolision，这是一种基于学习的方法，可以综合无碰撞3D人类姿势。在我们方法的症结中，我们的一种新颖的深度建筑，同时解码了潜在空间的新人类姿势，并预测了碰撞的身体部位。我们体系结构的这两个组成部分被用作目标函数，并在无碰撞的人类姿势产生的约束优化中替代硬性约束。我们方法的一个新颖方面是使用双重自动编码器，将全身碰撞分解为局部身体部位之间的碰撞群体。通过解决受限的优化，我们表明可以解决大量的碰撞伪像。此外，在$ 2.5 \ times 10^6 $ scape的$ 2.5 \ times 10^6 $的大型测试集中，我们的体系结构实现了碰撞预测的准确性$ 94.1 \％\％$ $，$ 80 \ times $ $ $加速，而精确的碰撞检测算法。据我们所知，Lcolision是第一种加速碰撞检测并使用神经网络解决渗透率的方法。
We present LCollision, a learning-based method that synthesizes collision-free 3D human poses. At the crux of our approach is a novel deep architecture that simultaneously decodes new human poses from the latent space and predicts colliding body parts. These two components of our architecture are used as the objective function and surrogate hard constraints in a constrained optimization for collision-free human pose generation. A novel aspect of our approach is the use of a bilevel autoencoder that decomposes whole-body collisions into groups of collisions between localized body parts. By solving the constrained optimizations, we show that a significant amount of collision artifacts can be resolved. Furthermore, in a large test set of $2.5\times 10^6$ randomized poses from SCAPE, our architecture achieves a collision-prediction accuracy of $94.1\%$ with $80\times$ speedup over exact collision detection algorithms. To the best of our knowledge, LCollision is the first approach that accelerates collision detection and resolves penetrations using a neural network.
