8 papers
ReCHOIR: Contact-guided Human Object Interaction Retargeting to Diverse Characters
Chaelin Kim, Seokhyeon Hong, Kwan Yun +3
We present ReCHOIR, a novel contact-guided motion retargeting method for transferring human object interaction (HOI) motions across diverse humanoid characters. Unlike prior motion…
Skinned Motion Retargeting via Artifact-driven Kinematic Prior Refinement
Seokhyeon Hong, Chaelin Kim, Inseo Jang +2
Motion retargeting aims to transfer a source motion to target characters with different skeletal structures, proportions, and body shapes. Although recent neural retargeting method…
Skinned Motion Retargeting with Spatially Adaptive Interaction Guidance
Soojin Choi, Seokhyeon Hong, Chaelin Kim +3
Retargeting motion across characters with varying body shapes while preserving interaction semantics, such as self-contact and near-body proximity, remains a challenging problem. W…
Stylized Text-to-Motion Generation via Hypernetwork-Driven Low-Rank Adaptation
Junhyuk Jeon, Seokhyeon Hong, Junyong Noh
Text-driven motion diffusion models are capable of generating realistic human motions, but text alone often struggles to express fine-level nuances of motion, commonly referred to…
X-AVDT: Audio-Visual Cross-Attention for Robust Deepfake Detection
Youngseo Kim, Kwan Yun, Seokhyeon Hong +3
The surge of highly realistic synthetic videos produced by contemporary generative systems has significantly increased the risk of malicious use, challenging both humans and existi…
SALAD: Skeleton-aware Latent Diffusion for Text-driven Motion Generation and Editing
Seokhyeon Hong, Chaelin Kim, Serin Yoon +3
Text-driven motion generation has advanced significantly with the rise of denoising diffusion models. However, previous methods often oversimplify representations for the skeletal…
ASMR: Adaptive Skeleton-Mesh Rigging and Skinning via 2D Generative Prior
Seokhyeon Hong, Soojin Choi, Chaelin Kim +2
Despite the growing accessibility of skeletal motion data, integrating it for animating character meshes remains challenging due to diverse configurations of both skeletons and mes…
AnyMoLe: Any Character Motion In-betweening Leveraging Video Diffusion Models
Kwan Yun, Seokhyeon Hong, Chaelin Kim +1
Despite recent advancements in learning-based motion in-betweening, a key limitation has been overlooked: the requirement for character-specific datasets. In this work, we introduc…