Skeleton Subspace Skin Penetration Removal

深層学習による二次元・三次元化粧表現の研究と応用

動画におけるアイデンティティを保持したメイク転写手法

A Diffusion-Based Framework for Human-Object Interaction Synthesis via Pose-Grasp Decoupling

Neural Multi-View Self-Calibrated Photometric Stereo without Photometric Stereo Cues

FreeUV: Ground-Truth-Free Realistic Facial UV Texture Recovery via Cross-Assembly Inference Strategy

V-PartSwap: Motion-Consistent Facial Part Transfer in Videos via Alignment-Aware Diffusion

KaoLRM: Repurposing Pre-trained Large Reconstruction Models for Parametric 3D Face Reconstruction

DeMapGS: Simultaneous Mesh Deformation and Surface Attribute Mapping via Gaussian Splatting

Structured Gaussian Splatting via Surface Deformation

FreeEyeglass: Training-free and Mask-free Eyeglass Transfer for Facial Videos

TANGO: Co-Speech Gesture Video Reenactment with Hierarchical Audio Motion Embedding and Diffusion Interpolation

ShadowSG: Spherical Gaussian Illumination from Shadows

BeautyBank: Encoding Facial Makeup in Latent Space

BeautyBank: Encoding Facial Makeup in a Latent Space for Enhanced Makeup Applications

多視点動画からの一貫した三次元顔メッシュ生成手法の検証と性能改善の検討

SynthMakeup: A Large-Scale Photo-Realistic Synthetic Makeup Dataset

Spherical Gaussian Illumination from a Single Image via Shadow Clues

VideoMotionGraph++: Co-Speech Gesture Video Reenactment with Blending Diffusion Model and Neural Rhythm Embedding

Lang4D: Weakly Supervised Learning of 4D Language Splatting

Makeup Prior Models for 3D Facial Makeup Estimation and Applications