Song-Hai Zhang

papers

1,430

total citations

papers (21)

Wonder3D: Single Image to 3D using Cross-Domain Diffusion

CVPR 2024arXiv

672

citations

Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformers

CVPR 2024arXiv

278

citations

MeGA: Hybrid Mesh-Gaussian Head Avatar for High-Fidelity Rendering and Head Editing

CVPR 2025arXiv

citations

MBPTrack: Improving 3D Point Cloud Tracking with Memory Networks and Box Priors

ICCV 2023arXiv

citations

PI3D: Efficient Text-to-3D Generation with Pseudo-Image Diffusion

CVPR 2024arXiv

citations

GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors

ICCV 2025arXiv

citations

DreamComposer: Controllable 3D Object Generation via Multi-View Conditions

CVPR 2024arXiv

citations

PanoGRF: Generalizable Spherical Radiance Fields for Wide-baseline Panoramas

NEURIPS 2023arXiv

citations

DualVector: Unsupervised Vector Font Synthesis With Dual-Part Representation

CVPR 2023arXiv

citations

Splatter-360: Generalizable 360 Gaussian Splatting for Wide-baseline Panoramic Images

CVPR 2025

citations

PPEA-Depth: Progressive Parameter-Efficient Adaptation for Self-Supervised Monocular Depth Estimation

AAAI 2024arXiv

citations

DepthSync: Diffusion Guidance-Based Depth Synchronization for Scale- and Geometry-Consistent Video Depth Estimation

ICCV 2025arXiv

citations

SVG-Head: Hybrid Surface-Volumetric Gaussians for High-Fidelity Head Reconstruction and Real-Time Editing

ICCV 2025arXiv

citations

Joint Implicit Neural Representation for High-fidelity and Compact Vector Fonts

ICCV 2023

citations

Face2Faceρ: Real-Time High-Resolution One-Shot Face Reenactment

ECCV 2022

citations

NeuFrameQ: Neural Frame Fields for Scalable and Generalizable Anisotropic Quadrangulation

ICCV 2025

citations

SafeTeleport: Potential Field-Guided Teleportation for Personal Space Protection in Social VR

ISMAR 2025

citations

Can the Perceived Capability of Your Virtual Avatar Enhance Exercise Performance?

ISMAR 2025

citations

Song-Hai Zhang

papers (21)

Wonder3D: Single Image to 3D using Cross-Domain Diffusion

Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformers

NeRFReN: Neural Radiance Fields With Reflections

Sketch2Model: View-Aware 3D Modeling From Single Free-Hand Sketches

CXTrack: Improving 3D Point Cloud Tracking With Contextual Information

MeGA: Hybrid Mesh-Gaussian Head Avatar for High-Fidelity Rendering and Head Editing

MBPTrack: Improving 3D Point Cloud Tracking with Memory Networks and Box Priors

PI3D: Efficient Text-to-3D Generation with Pseudo-Image Diffusion

GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors

DreamComposer: Controllable 3D Object Generation via Multi-View Conditions

PanoGRF: Generalizable Spherical Radiance Fields for Wide-baseline Panoramas

DualVector: Unsupervised Vector Font Synthesis With Dual-Part Representation

Splatter-360: Generalizable 360 Gaussian Splatting for Wide-baseline Panoramic Images

PPEA-Depth: Progressive Parameter-Efficient Adaptation for Self-Supervised Monocular Depth Estimation

DepthSync: Diffusion Guidance-Based Depth Synchronization for Scale- and Geometry-Consistent Video Depth Estimation

SVG-Head: Hybrid Surface-Volumetric Gaussians for High-Fidelity Head Reconstruction and Real-Time Editing

Joint Implicit Neural Representation for High-fidelity and Compact Vector Fonts

Face2Faceρ: Real-Time High-Resolution One-Shot Face Reenactment

NeuFrameQ: Neural Frame Fields for Scalable and Generalizable Anisotropic Quadrangulation

SafeTeleport: Potential Field-Guided Teleportation for Personal Space Protection in Social VR

Can the Perceived Capability of Your Virtual Avatar Enhance Exercise Performance?

papers (21)

Wonder3D: Single Image to 3D using Cross-Domain Diffusion

Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformers

NeRFReN: Neural Radiance Fields With Reflections

Sketch2Model: View-Aware 3D Modeling From Single Free-Hand Sketches

CXTrack: Improving 3D Point Cloud Tracking With Contextual Information

MeGA: Hybrid Mesh-Gaussian Head Avatar for High-Fidelity Rendering and Head Editing

MBPTrack: Improving 3D Point Cloud Tracking with Memory Networks and Box Priors

PI3D: Efficient Text-to-3D Generation with Pseudo-Image Diffusion

GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors

DreamComposer: Controllable 3D Object Generation via Multi-View Conditions

PanoGRF: Generalizable Spherical Radiance Fields for Wide-baseline Panoramas

DualVector: Unsupervised Vector Font Synthesis With Dual-Part Representation

Splatter-360: Generalizable 360 Gaussian Splatting for Wide-baseline Panoramic Images

PPEA-Depth: Progressive Parameter-Efficient Adaptation for Self-Supervised Monocular Depth Estimation

DepthSync: Diffusion Guidance-Based Depth Synchronization for Scale- and Geometry-Consistent Video Depth Estimation

SVG-Head: Hybrid Surface-Volumetric Gaussians for High-Fidelity Head Reconstruction and Real-Time Editing

Joint Implicit Neural Representation for High-fidelity and Compact Vector Fonts

Face2Faceρ: Real-Time High-Resolution One-Shot Face Reenactment

NeuFrameQ: Neural Frame Fields for Scalable and Generalizable Anisotropic Quadrangulation

SafeTeleport: Potential Field-Guided Teleportation for Personal Space Protection in Social VR

Can the Perceived Capability of Your Virtual Avatar Enhance Exercise Performance?