2 citations · 3 across the 3 of their papers we have counts for
7 papers
Recovering Black-Box Point Cloud Models from Pose Shifts via Derivative-Free Optimization
Seonghwan Park, Min-Gyu Park
Point cloud models are increasingly deployed through score-only black-box interfaces. Under this access model, test-time rotations outside the training distribution can substantial…
URHead: A Unified UV-Space Representation for Joint Mesh-3DGS Optimization in Head Avatars
Seonghak Lee, Junhee Cho, Jisoo Park +4
We present URHead, a unified representation for high-fidelity and animatable head avatars that fundamentally redefines mesh-Gaussian integration. While mesh-based methods offer pre…
JacobianAvatar: Temporally Consistent Semi-rigid Avatar Reconstruction from a Monocular Video
Changyeon Won, Min-Gyu Park, Seonghwan Park +2
Generating realistic human avatars in complex motions--such as clothing dynamics--requires modeling of global and local deformations which remains challenging in monocular settings…
PIAvatar: Physically Interactive Avatars via Deformation Gradient Decoupling
Sang-Hun Han, Min-Gyu Park, Jisu Shin +3
3D human avatars have shown impressive visual fidelity driven by pose-conditioned models, yet they still lack the physical ability required for interactions with each other and env…
CanonicalFusion: Generating Drivable 3D Human Avatars from Multiple Images
Jisu Shin, Junmyeong Lee, Seongmin Lee +4
We present a novel framework for reconstructing animatable human avatars from multiple images, termed CanonicalFusion. Our central concept involves integrating individual reconstru…
High-fidelity 3D Human Digitization from Single 2K Resolution Images
Sang-Hun Han, Min-Gyu Park, Ju Hong Yoon +3
High-quality 3D human body reconstruction requires high-fidelity and large-scale training data and appropriate network design that effectively exploits the high-resolution input im…
Monocular Human Digitization via Implicit Re-projection Networks
Min-Gyu Park, Ju-Mi Kang, Je Woo Kim +1
We present an approach to generating 3D human models from images. The key to our framework is that we predict double-sided orthographic depth maps and color images from a single pe…