Purposer：将人体运动生成置于情境中
Purposer: Putting Human Motion Generation in Context
AI总结：
提出Purposer方法，基于神经离散表示学习和自回归生成，利用多种情境条件（如路径、姿态、场景点云）生成高质量、多样化的3D室内人体运动，优于现有专门方法。
摘要：
我们提出了一种新颖的方法，用于生成人体运动以填充3D室内场景。该方法可通过多种条件信号的组合进行控制，例如场景中的路径、目标姿态、过往运动以及以3D点云表示的场景。现有最先进的方法要么是专门针对单一设置的模型，要么需要大量高质量且多样化的训练数据，要么是无法整合场景或其他情境信息的无条件模型。因此，它们适用性有限且依赖昂贵的训练数据。为解决这些局限性，我们提出了一种基于神经离散表示学习的新方法，名为Purposer。我们的模型能够灵活利用开放获取的大规模数据集（如AMASS）中已有的不同类型信息。首先，我们将无条件人体运动编码到离散潜在空间中。其次，一个以关键情境信息为条件（通过提示或附加标记）并在该空间中进行下一步预测训练的自回归生成模型，合成潜在索引序列。我们进一步设计了一个新颖的条件模块，通过使用具有两个分支的网络计算独立的特征堆栈，来处理这种因果模型中的未来条件信息。通过这种方式，Purposer能够在多样化的测试场景中生成逼真的运动序列。通过详尽的评估，我们证明了我们的多情境解决方案在质量和多样性方面均优于针对特定情境信息的现有专门方法。我们的模型使用短序列进行训练，但能够使用各种条件信号的一个副产品是，在测试时，不同的组合可用于将短序列串联起来，在情境场景中生成长时间的运动。
英文摘要：
We present a novel method to generate human motion to populate 3D indoor scenes. It can be controlled with various combinations of conditioning signals such as a path in a scene, target poses, past motions, and scenes represented as 3D point clouds. State-of-the-art methods are either models specialized to one single setting, require vast amounts of high-quality and diverse training data, or are unconditional models that do not integrate scene or other contextual information. As a consequence, they have limited applicability and rely on costly training data. To address these limitations, we propose a new method ,dubbed Purposer, based on neural discrete representation learning. Our model is capable of exploiting, in a flexible manner, different types of information already present in open access large-scale datasets such as AMASS. First, we encode unconditional human motion into a discrete latent space. Second, an autoregressive generative model, conditioned with key contextual information, either with prompting or additive tokens, and trained for next-step prediction in this space, synthesizes sequences of latent indices. We further design a novel conditioning block to handle future conditioning information in such a causal model by using a network with two branches to compute separate stacks of features. In this manner, Purposer can generate realistic motion sequences in diverse test scenes. Through exhaustive evaluation, we demonstrate that our multi-contextual solution outperforms existing specialized approaches for specific contextual information, both in terms of quality and diversity. Our model is trained with short sequences, but a byproduct of being able to use various conditioning signals is that at test time different combinations can be used to chain short sequences together and generate long motions within a context scene.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
