Large and high-quality motion datasets are essential for advancing human motion modeling. However, limitations of existing motion datasets, such as insufficient scale or inadequate quality, significantly hinder the progress of this field. To address these limitations, we introduce Mimic-X, a large-scale (52 hours), physically plausible 3D human motion dataset. To construct Mimic-X, we develop an adaptive option framework that controls a physically simulated character to imitate low-quality motions extracted from a vast collection of online videos. Specifically, we first apply hierarchical clustering to group motions into clusters, and then train option policies to mimic motions sampled from these clusters. Considering the noisy nature of low-quality motions, we utilize a separate encoder for each cluster to map the noisy motions within the cluster into a compact latent space. This significantly enhances the quality of the imitated motions while accelerating the learning process. Subsequently, we employ dynamic programming as a meta-policy to efficiently organize the option policies to generate complete motion clips. Finally, we perform fine-tuning to each motion sequence to further refine motion quality. The proposed adaptive option framework outperforms state-of-the-art human motion recovery methods across various evaluation metrics, demonstrating that motions in Mimic-X exhibit higher quality and greater physical plausibility. Furthermore, experimental results show that Mimic-X enhances the performance of motion generation methods, verifying its effectiveness for motion modeling tasks.

Abstract The emergence of position‐based simulation approaches has quickly developed a group of new topics in the computer graphics community. These approaches are popular due to their advantages, including computational efficiency, controllability, stability and robustness for different scenarios, whilst they also have some weaknesses. In this survey, we will introduce the concept of the baseline position based dynamics (PBD) method and review the improvements and applications of PBD since 2018, including extensions for different materials and integrations with other techniques.

Online games require small data of 3D models for low storage costs, quick transmission over the Internet, and efficient geometric processing to achieve real-time performance, and new techniques of facial blendshapes to create natural facial animation. Current geometric modelling and animation techniques involve big data of geometric models and widely applied facial animation using linear interpolation cannot generate natural facial animation and create special facial animation effects. In this paper, we propose a new approach to integrate the strengths of ODE (ordinary differential equation) sweeping surfaces and Newton’s second law-based facial blendshapes to create 3D models and their animation with small data, high efficiency, and ability to create special facial effects.