8 citations · 8 across the 4 of their papers we have counts for
4 papers · 1 filter
EDGAR: Efficient Diffusion-Driven Gaussian Avatar Refinement via Synthetic Failure
Kwan Yun, Minhyeok Bang, Colette Suhjung Koo +1
Recent advances in Gaussian splatting have enabled efficient and photorealistic head avatar reconstruction, yet monocular video-based or image-based methods still suffer from under…
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…
AnyTalk: Speech Animation for Arbitrary Characters Leveraging a Video Generation Model
Kwan Yun, Serin Yoon, Sunjin Jung +3
We present AnyTalk, a novel method for generating 3D speech animations for arbitrary characters without requiring any animation data. While existing audio-driven 3D speech animatio…
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…