Publication Type

Journal Article

Version

publishedVersion

Publication Date

4-2023

Abstract

Anime is an abstract art form that is substantially different from the human portrait, leading to a challenging misaligned image translation problem that is beyond the capability of existing methods. This can be boiled down to a highly ambiguous unconstrained translation between two domains. To this end, we design a new anime translation framework by deriving the prior knowledge of a pre-Trained StyleGAN model. We introduce disentangled encoders to separately embed structure and appearance information into the same latent code, governed by four tailored losses. Moreover, we develop a FaceBank aggregation method that leverages the generated data of the StyleGAN, anchoring the prediction to produce in-domain animes. To empower our model and promote the research of anime translation, we propose the first anime portrait parsing dataset, Danbooru-Parsing, containing 4,921 densely labeled images across 17 classes. This dataset connects the face semantics with appearances, enabling our new constrained translation setting. We further show the editability of our results, and extend our method to manga images, by generating the first manga parsing pseudo data. Extensive experiments demonstrate the values of our new dataset and method, resulting in the first feasible solution on anime translation.

Keywords

Abstract arts, Aggregation methods, Anchorings, Feasible solution, Image editing, Image translation, Image-to-image translation, Labeled images, Prior-knowledge, Two domains

Discipline

Databases and Information Systems

Research Areas

Information Systems and Management

Publication

ACM Transactions on Graphics

Volume

42

Issue

3

ISSN

0730-0301

Identifier

10.1145/3585002

Publisher

Association for Computing Machinery (ACM)

Additional URL

https://doi.org/10.1145/3585002

Share

COinS