Yichun Shi

papers

1,516

total citations

papers (12)

MVDream: Multi-view Diffusion for 3D Generation

ICLR 2024arXiv

880

citations

Towards Universal Representation Learning for Deep Face Recognition

CVPR 2020arXiv

161

citations

MagicPose: Realistic Human Poses and Facial Expressions Retargeting with Identity-aware Diffusion

ICML 2024arXiv

113

citations

SemanticStyleGAN: Learning Compositional Generative Priors for Controllable Image Synthesis and Editing

CVPR 2022arXiv

107

citations

PAniC-3D: Stylized Single-View 3D Reconstruction From Portraits of Anime Characters

CVPR 2023arXiv

citations

X-Dyna: Expressive Dynamic Human Image Animation

CVPR 2025arXiv

citations

Enhancing 3D Fidelity of Text-to-3D using Cross-View Correspondences

CVPR 2024arXiv

citations

PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360deg

CVPR 2023

citations

Yichun Shi

papers (12)

MVDream: Multi-view Diffusion for 3D Generation

Towards Universal Representation Learning for Deep Face Recognition

MagicPose: Realistic Human Poses and Facial Expressions Retargeting with Identity-aware Diffusion

SemanticStyleGAN: Learning Compositional Generative Priors for Controllable Image Synthesis and Editing

Lifting 2D StyleGAN for 3D-Aware Face Generation

Dual Diffusion for Unified Image Generation and Understanding

OmniAvatar: Geometry-Guided Controllable 3D Head Synthesis

DiffPortrait3D: Controllable Diffusion for Zero-Shot Portrait View Synthesis

PAniC-3D: Stylized Single-View 3D Reconstruction From Portraits of Anime Characters

X-Dyna: Expressive Dynamic Human Image Animation

Enhancing 3D Fidelity of Text-to-3D using Cross-View Correspondences

PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360deg

papers (12)

MVDream: Multi-view Diffusion for 3D Generation

Towards Universal Representation Learning for Deep Face Recognition

MagicPose: Realistic Human Poses and Facial Expressions Retargeting with Identity-aware Diffusion

SemanticStyleGAN: Learning Compositional Generative Priors for Controllable Image Synthesis and Editing

Lifting 2D StyleGAN for 3D-Aware Face Generation

Dual Diffusion for Unified Image Generation and Understanding

OmniAvatar: Geometry-Guided Controllable 3D Head Synthesis

DiffPortrait3D: Controllable Diffusion for Zero-Shot Portrait View Synthesis

PAniC-3D: Stylized Single-View 3D Reconstruction From Portraits of Anime Characters

X-Dyna: Expressive Dynamic Human Image Animation

Enhancing 3D Fidelity of Text-to-3D using Cross-View Correspondences

PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360deg