Abstract
The production of cartoon animation is a very expensive and time-consuming task even for experienced animators because smooth motions are required to create cartoon-style animations that are expressive and stylized. If it is possible to provide a reusable technique, we can efficiently produce new animations that have similar motion styles but different cartoon characters. In this paper, we provide a novel method which can extract motions from existing animation sequences and retarget them to other cartoon characters. Specifically, we implement a skeleton correspondence construction method to extract the motion information from the existing animation sequence, and apply inverse kinematics (IK) to transform the motion onto the target skeleton. The proposed cartoon reusing method can efficiently reduce the workload on the animator and accelerate the development of animation industry. The experimental results conducted on our cartoon dataset suggest the effectiveness of the proposed methods for cartoon animation reusing.
| Original language | English |
|---|---|
| Pages (from-to) | 461-468 |
| Number of pages | 8 |
| Journal | Neurocomputing |
| Volume | 120 |
| DOIs | |
| State | Published - 23 Nov 2013 |
| Externally published | Yes |
Keywords
- Animation reusing
- Correspondence construction
- Motion data generation
Fingerprint
Dive into the research topics of 'Skeleton correspondence construction and its applications in animation style reusing'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver