no code implementations • 8 Mar 2024 • Junsu Kim, Yunhoe Ku, Jihyeon Kim, Junuk Cha, Seungryul Baek
This technique uses Vision-Language Model (VLM) to verify the correctness of pseudo ground-truths (GTs) without requiring additional model training.
no code implementations • 28 Dec 2023 • Hansol Lee, Junuk Cha, Yunhoe Ku, Jae Shin Yoon, Seungryul Baek
For implicit modeling, an implicit network combines the appearance and 3D motion features to decode high-fidelity clothed 3D human avatars with motion-dependent geometry and texture.
no code implementations • 8 Jun 2023 • Hansol Lee, Yunhoe Ku, Eunseo Kim, Seungryul Baek
We proposed IFaceUV, a fully differentiable pipeline that properly combines 2D and 3D information to conduct the facial reenactment task.