no code implementations • 14 Feb 2024 • Dongseok Yang, Jiho Kang, Lingni Ma, Joseph Greer, Yuting Ye, Sung-Hee Lee
We then condition the otherwise ambiguous lower-body pose with the predictions of foot contact and upper-body pose in a two-stage model.
no code implementations • 26 Dec 2023 • Seungchan Lim, Sumin Kim, Sung-Hee Lee
This paper presents a novel method for reconstructing 3D garment models from a single image of a posed user.
no code implementations • 24 Oct 2023 • Hyun-Song Kwon, Sung-Hee Lee
Realistic reconstruction of 3D clothing from an image has wide applications, such as avatar creation and virtual try-on.
no code implementations • 16 Oct 2023 • Deok-Kyeong Jang, Yuting Ye, Jungdam Won, Sung-Hee Lee
Central to our framework is the Neural Context Matcher, which generates a motion feature for the target character with the most similar context to the input motion feature.
no code implementations • 17 Sep 2023 • Deok-Kyeong Jang, Dongseok Yang, Deok-Yun Jang, Byeoli Choi, Taeil Jin, Sung-Hee Lee
In such applications, precise full-body tracking is essential for an immersive experience and a sense of embodiment with the virtual avatar.
1 code implementation • 10 Feb 2022 • Deok-Kyeong Jang, Soomin Park, Sung-Hee Lee
The Motion Puzzle is the first that can control the motion style of individual body parts, allowing for local style editing and significantly increasing the range of stylized motions.
1 code implementation • 31 Jan 2022 • Maria Korosteleva, Sung-Hee Lee
The fields of SocialVR, performance capture, and virtual try-on are often faced with a need to faithfully reproduce real garments in the virtual world.
2 code implementations • 12 Sep 2021 • Maria Korosteleva, Sung-Hee Lee
Our method consists of a flexible description structure for specifying parametric sewing pattern templates and the automatic generation pipeline to produce garment 3D models with little-to-none manual intervention.
no code implementations • 7 Jul 2021 • Taehei Kim, Sung-Hee Lee
Specifically, our framework can generate quadruped locomotion on flat elastic terrain that consists of a matrix of tiles moving up and down passively when pushed by the robot's feet.
no code implementations • 22 Dec 2020 • Leonard Yoon, Dongseok Yang, Jaehyun Kim, Choongho Chung, Sung-Hee Lee
In this paper, we present novel methods to determine the avatar's position in an indoor space to preserve the semantics of the user's position in a dissimilar indoor space with different space configurations and furniture layouts.
Human-Computer Interaction