Skip to main content

Few-shot anime pose transfer.

Wang, P., Yang, K, Yuan, C, Li, H, Tang, W and Yang, X, 2024. Few-shot anime pose transfer. Visual Computer. (In Press)

Full text available as:

[img]
Preview
PDF (OPEN ACCESS ARTICLE)
s00371-024-03447-7.pdf - Published Version
Available under License Creative Commons Attribution.

6MB

DOI: 10.1007/s00371-024-03447-7

Abstract

In this paper, we propose a few-shot method for pose transfer of anime characters—given a source image of an anime character and a target pose, we transfer the pose of the target to the source character. Despite recent advances in pose transfer on real people images, these methods typically require large numbers of training images of different person under different poses to achieve reasonable results. However, anime character images are expensive to obtain they are created with a lot of artistic authoring. To address this, we propose a meta-learning framework for few-shot pose transfer, which can well generalize to an unseen character given just a few examples of the character. Further, we propose fusion residual blocks to align the features of the source and target so that the appearance of the source character can be well transferred to the target pose. Experiments show that our method outperforms leading pose transfer methods, especially when the source characters are not in the training set.

Item Type:Article
ISSN:0178-2789
Group:Faculty of Media & Communication
ID Code:39944
Deposited By: Symplectic RT2
Deposited On:10 Jun 2024 10:47
Last Modified:10 Jun 2024 10:47

Downloads

Downloads per month over past year

More statistics for this item...
Repository Staff Only -