VidAnimator: User-Guided Stylized 3D Character Animation from Human Videos
Xinwu Ye, Jun-Hsiang Yao, Jielin Feng, Shuhong Mei, Xingyu Lan, Siming Chen

TL;DR
VidAnimator is a user-guided system that converts human videos into stylized 3D character animations, significantly simplifying the animation process with interactive tools and customizable options.
Contribution
It introduces a mixed-initiative framework and interactive tools for transferring motion from videos to stylized 3D characters, enabling intuitive customization.
Findings
The system produces natural stylized animations similar to input videos.
User studies confirm the effectiveness of the framework.
Case studies demonstrate diverse animation results.
Abstract
With captivating visual effects, stylized 3D character animation has gained widespread use in cinematic production, advertising, social media, and the potential development of virtual reality (VR) non-player characters (NPCs). However, animating stylized 3D characters often requires significant time and effort from animators. We propose a mixed-initiative framework and interactive system to enable stylized 3D characters to mimic motion in human videos. The framework takes a single-view human video and a stylized 3D character (the target character) as input, captures the motion of the video, and then transfers the motion to the target character. In addition, it involves two interaction modules for customizing the result. Accordingly, the system incorporates two authoring tools that empower users with intuitive modification. A questionnaire study offers tangible evidence of the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsHuman Motion and Animation · Artificial Intelligence in Games · 3D Shape Modeling and Analysis
