Yan-Pei Cao

papers

2,102

total citations

papers (26)

SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes

CVPR 2024arXiv

311

citations

SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution With Skip-Transformer

ICCV 2021arXiv

296

citations

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

CVPR 2024arXiv

278

citations

PMP-Net: Point Cloud Completion by Learning Multi-Step Point Moving Paths

CVPR 2021arXiv

205

citations

Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Models

CVPR 2023arXiv

188

citations

DreamAvatar: Text-and-Shape Guided 3D Human Avatar Generation via Diffusion Models

CVPR 2024arXiv

174

citations

DeVRF: Fast Deformable Voxel Radiance Fields for Dynamic Scenes

NEURIPS 2022arXiv

139

citations

Cycle4Completion: Unpaired Point Cloud Completion Using Cycle Transformation With Missing Region Coding

CVPR 2021arXiv

109

citations

DoubleField: Bridging the Neural Surface and Radiance Fields for High-Fidelity Human Reconstruction and Rendering

CVPR 2022arXiv

citations

EpiDiff: Enhancing Multi-View Synthesis via Localized Epipolar-Constrained Diffusion

CVPR 2024arXiv

citations

MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation

CVPR 2025arXiv

citations

SurfelNeRF: Neural Surfel Radiance Fields for Online Photorealistic Reconstruction of Indoor Scenes

CVPR 2023arXiv

citations

HOSNeRF: Dynamic Human-Object-Scene Neural Radiance Fields from a Single Video

ICCV 2023arXiv

citations

DynVideo-E: Harnessing Dynamic NeRF for Large-Scale Motion- and View-Change Human-Centric Video Editing

CVPR 2024arXiv

citations

HumanRef: Single Image to 3D Human Generation via Reference-Guided Diffusion

CVPR 2024arXiv

citations

PanoGRF: Generalizable Spherical Radiance Fields for Wide-baseline Panoramas

NEURIPS 2023arXiv

citations

ConTex-Human: Free-View Rendering of Human from a Single Image with Texture-Consistent Synthesis

CVPR 2024arXiv

citations

Speech2Lip: High-fidelity Speech to Lip Generation by Learning from a Short Video

ICCV 2023arXiv

citations

PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing

CVPR 2025arXiv

citations

DI-PCG: Diffusion-based Efficient Inverse Procedural Content Generation for High-quality 3D Asset Creation

CVPR 2025arXiv

citations

HRDFuse: Monocular 360deg Depth Estimation by Collaboratively Learning Holistic-With-Regional Depth Distributions

CVPR 2023

citations

CL-NeRF: Continual Learning of Neural Radiance Fields for Evolving Scene Representation

NEURIPS 2023

citations

SparseGNV: Generating Novel Views of Indoor Scenes with Sparse RGB-D Images

AAAI 2024

citations

Yan-Pei Cao

papers (26)

SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes

SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution With Skip-Transformer

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

PMP-Net: Point Cloud Completion by Learning Multi-Step Point Moving Paths

Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Models

DreamAvatar: Text-and-Shape Guided 3D Human Avatar Generation via Diffusion Models

DeVRF: Fast Deformable Voxel Radiance Fields for Dynamic Scenes

Cycle4Completion: Unpaired Point Cloud Completion Using Cycle Transformation With Missing Region Coding

DoubleField: Bridging the Neural Surface and Radiance Fields for High-Fidelity Human Reconstruction and Rendering

EpiDiff: Enhancing Multi-View Synthesis via Localized Epipolar-Constrained Diffusion

MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation

SurfelNeRF: Neural Surfel Radiance Fields for Online Photorealistic Reconstruction of Indoor Scenes

HOSNeRF: Dynamic Human-Object-Scene Neural Radiance Fields from a Single Video

DynVideo-E: Harnessing Dynamic NeRF for Large-Scale Motion- and View-Change Human-Centric Video Editing

HumanRef: Single Image to 3D Human Generation via Reference-Guided Diffusion

PanoGRF: Generalizable Spherical Radiance Fields for Wide-baseline Panoramas

ConTex-Human: Free-View Rendering of Human from a Single Image with Texture-Consistent Synthesis

Speech2Lip: High-fidelity Speech to Lip Generation by Learning from a Short Video

PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing

Deformable Radial Kernel Splatting

SC-NeuS: Consistent Neural Surface Reconstruction from Sparse and Noisy Views

OmniZoomer: Learning to Move and Zoom in on Sphere at High-Resolution

DI-PCG: Diffusion-based Efficient Inverse Procedural Content Generation for High-quality 3D Asset Creation

HRDFuse: Monocular 360deg Depth Estimation by Collaboratively Learning Holistic-With-Regional Depth Distributions

CL-NeRF: Continual Learning of Neural Radiance Fields for Evolving Scene Representation

SparseGNV: Generating Novel Views of Indoor Scenes with Sparse RGB-D Images

papers (26)

SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes

SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution With Skip-Transformer

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

PMP-Net: Point Cloud Completion by Learning Multi-Step Point Moving Paths

Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Models

DreamAvatar: Text-and-Shape Guided 3D Human Avatar Generation via Diffusion Models

DeVRF: Fast Deformable Voxel Radiance Fields for Dynamic Scenes

Cycle4Completion: Unpaired Point Cloud Completion Using Cycle Transformation With Missing Region Coding

DoubleField: Bridging the Neural Surface and Radiance Fields for High-Fidelity Human Reconstruction and Rendering

EpiDiff: Enhancing Multi-View Synthesis via Localized Epipolar-Constrained Diffusion

MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation

SurfelNeRF: Neural Surfel Radiance Fields for Online Photorealistic Reconstruction of Indoor Scenes

HOSNeRF: Dynamic Human-Object-Scene Neural Radiance Fields from a Single Video

DynVideo-E: Harnessing Dynamic NeRF for Large-Scale Motion- and View-Change Human-Centric Video Editing

HumanRef: Single Image to 3D Human Generation via Reference-Guided Diffusion

PanoGRF: Generalizable Spherical Radiance Fields for Wide-baseline Panoramas

ConTex-Human: Free-View Rendering of Human from a Single Image with Texture-Consistent Synthesis

Speech2Lip: High-fidelity Speech to Lip Generation by Learning from a Short Video

PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing

Deformable Radial Kernel Splatting

SC-NeuS: Consistent Neural Surface Reconstruction from Sparse and Noisy Views

OmniZoomer: Learning to Move and Zoom in on Sphere at High-Resolution

DI-PCG: Diffusion-based Efficient Inverse Procedural Content Generation for High-quality 3D Asset Creation

HRDFuse: Monocular 360deg Depth Estimation by Collaboratively Learning Holistic-With-Regional Depth Distributions

CL-NeRF: Continual Learning of Neural Radiance Fields for Evolving Scene Representation

SparseGNV: Generating Novel Views of Indoor Scenes with Sparse RGB-D Images