43-Issue 8

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/3607035

Browse

Browsing 43-Issue 8 by Subject "CCS Concepts: Computing methodologies → Motion processing"

Now showing 1 - 1 of 1
  • Thumbnail Image
    Item
    Pose-to-Motion: Cross-Domain Motion Retargeting with Pose Prior
    (The Eurographics Association and John Wiley & Sons Ltd., 2024) Zhao, Qingqing; Li, Peizhuo; Yifan, Wang; Sorkine-Hornung, Olga; Wetzstein, Gordon; Skouras, Melina; Wang, He
    Creating plausible motions for a diverse range of characters is a long-standing goal in computer graphics. Current learningbased motion synthesis methods rely on large-scale motion datasets, which are often difficult if not impossible to acquire. On the other hand, pose data is more accessible, since static posed characters are easier to create and can even be extracted from images using recent advancements in computer vision. In this paper, we tap into this alternative data source and introduce a neural motion synthesis approach through retargeting, which generates plausible motion of various characters that only have pose data by transferring motion from one single existing motion capture dataset of another drastically different characters. Our experiments show that our method effectively combines the motion features of the source character with the pose features of the target character, and performs robustly with small or noisy pose data sets, ranging from a few artist-created poses to noisy poses estimated directly from images. Additionally, a conducted user study indicated that a majority of participants found our retargeted motion to be more enjoyable to watch, more lifelike in appearance, and exhibiting fewer artifacts. Our code and dataset can be accessed here.