Seungkwon Kim

Seungkwon Kim

Auto-generated profile, based on publicly available information

Seungkwon Kim

NAVER WEBTOON Corp., South Korea

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 November 2022
Verified
Conference Paper
Open access
JBJihye Back
Jihye Back
SKSeungkwon Kim
Seungkwon Kim
NANamhyuk Ahn
Namhyuk Ahn
Full-body portrait stylization has drawn attention recently. However, most methods have focused only on converting face regions. A recently proposed two-stage method expands to full bodies, but the outputs are less plausible and fail to achieve quality robustness of non-face regions. Furthermore, they cannot reflect diverse skin tones. In this study, we propose a data-centric solution to build a production-level full-body portrait stylization system. We construct a novel and advanced dataset preparation paradigm that can effectively resolve the aforementioned problems.

25 May 2022 in arXiv
Verified
Preprint
Open access
PDF file
SKSeungkwon Kim
Seungkwon Kim
CGChaeheon Gwak
Chaeheon Gwak
DKDohyun Kim
Dohyun Kim
KLKwangho Lee
Kwangho Lee
JBJihye Back
Jihye Back
DKDaesik Kim
Daesik Kim
Cartoon domain has recently gained increasing popularity. Previous studies have attempted quality portrait stylization into the cartoon domain; however, this poses a great challenge since they have not properly addressed the critical constraints, such as requiring a large number of training images or the lack of support for abstract cartoon faces. Recently, a layer swapping method has been used for stylization requiring only a limited number of training images; however, its use cases are still narrow as it inherits the remaining issues. In this paper, we propose a novel method called Cross-domain Style mixing, which combines two latent codes from two different domains. Our method effectively stylizes faces into multiple cartoon characters at various face abstraction levels using only a single generator without even using a large number of training images.