컴퓨터 그래픽스 학회인 SIGGRAPH Asia 2018에 Motion AI 팀의 Deep Motion Transfer without Big Data 연구가 소개되었습니다.
Abstract
This paper presents a novel motion transfer algorithm that copies content motion into a specific style character. The input consists of two motions. One is a content motion such as walking or running, and the other is movement style such as zombie or Krall. The algorithm automatically generates the synthesized motion such as walking zombie, walking Krall, running zombie, or running Krall. In order to obtain natural results, the method adopts the generative power of deep neural networks. Compared to previous neural approaches, the proposed algorithm shows better quality, runs extremely fast, does not require big data, and supports user-controllable style weights.
Authors
Byungjun Kwon, Moonwon Yu, Hanyoung Jang, Hyundong Lee, Taesung Hahn(NCSOFT)
Proceeding
SIGGRAPH ‘18 ACM SIGGRAPH 2018 Posters Article No. 58