Pose-to-Motion: Cross-Domain Motion Retargeting with Pose Prior
This addresses the challenge of motion synthesis for characters in computer graphics where motion data is scarce, by leveraging more accessible pose data, though it is incremental as it builds on existing retargeting and synthesis methods.
The paper tackles the problem of generating believable motions for characters lacking motion data by retargeting motion from a source character with motion capture data to a target character with only pose data, even with different skeletons; experiments show it works robustly with small or noisy pose sets, and a user study found the retargeted motion more enjoyable, lifelike, and with fewer artifacts.
Creating believable motions for various characters has long been a goal in computer graphics. Current learning-based motion synthesis methods depend on extensive motion datasets, which are often challenging, if not impossible, to obtain. 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 utilize this alternative data source and introduce a neural motion synthesis approach through retargeting. Our method generates plausible motions for characters that have only pose data by transferring motion from an existing motion capture dataset of another character, which can have drastically different skeletons. 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. Project page: https://cyanzhao42.github.io/pose2motion