分解向量量化变分自编码器用于人类抓取生成
Decomposed Vector-Quantized Variational Autoencoder for Human Grasp Generation
AI总结：
本文提出分解向量量化变分自编码器（DVQ-VAE），通过分解手部编码和双阶段解码策略，提升人类抓取生成的逼真度，在四个基准上质量指标相对提升14.1%。
摘要：
生成逼真的人类抓取动作对于计算机图形学和机器人领域中涉及物体操作的应用来说是一项至关重要但又充满挑战的任务。现有方法通常难以生成精细逼真的人类抓取动作，以确保所有手指都能有效地与物体交互，因为它们侧重于将手作为一个整体表示进行编码，然后单步估计手的姿态和位置。在本文中，我们提出了一种新颖的分解向量量化变分自编码器（DVQ-VAE）来解决这一局限性，通过将手分解为几个不同的部分并分别进行编码。这种部分感知的分解架构有助于更精确地管理手的每个部分与物体之间的交互，从而增强生成的人类抓取动作的整体真实感。此外，我们设计了一种新的双阶段解码策略，首先在骨骼物理约束下确定抓取的类型，然后确定抓取的位置，这可以极大地提高模型的逼真度以及对未见手-物体交互的适应性。在实验中，与最先进的方法相比，我们的模型在四个广泛采用的基准测试中的质量指标上取得了约14.1%的相对提升。我们的源代码可在 https://github.com/florasion/D-VQVAE 获取。
英文摘要：
Generating realistic human grasps is a crucial yet challenging task for applications involving object manipulation in computer graphics and robotics. Existing methods often struggle with generating fine-grained realistic human grasps that ensure all fingers effectively interact with objects, as they focus on encoding hand with the whole representation and then estimating both hand posture and position in a single step. In this paper, we propose a novel Decomposed Vector-Quantized Variational Autoencoder (DVQ-VAE) to address this limitation by decomposing hand into several distinct parts and encoding them separately. This part-aware decomposed architecture facilitates more precise management of the interaction between each component of hand and object, enhancing the overall reality of generated human grasps. Furthermore, we design a newly dual-stage decoding strategy, by first determining the type of grasping under skeletal physical constraints, and then identifying the location of the grasp, which can greatly improve the verisimilitude as well as adaptability of the model to unseen hand-object interaction. In experiments, our model achieved about 14.1% relative improvement in the quality index compared to the state-of-the-art methods in four widely-adopted benchmarks. Our source code is available at https://github.com/florasion/D-VQVAE.
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。
