Yiyi Liao

papers

3,117

total citations

papers (23)

Towards Unsupervised Learning of Generative Models for 3D Controllable Image Synthesis

CVPR 2020arXiv

166

citations

HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting

CVPR 2024arXiv

139

citations

SMD-Nets: Stereo Mixture Density Networks

CVPR 2021arXiv

116

citations

On the Frequency Bias of Generative Models

NEURIPS 2021arXiv

citations

Learning Temporally Consistent Video Depth from Video Diffusion Priors

CVPR 2025arXiv

citations

UrbanGIRAFFE: Representing Urban Scenes as Compositional Generative Neural Feature Fields

ICCV 2023arXiv

citations

SteerNeRF: Accelerating NeRF Rendering via Smooth Viewpoint Trajectory

CVPR 2023arXiv

citations

Learning 3D-Aware Image Synthesis With Unknown Pose Distribution

CVPR 2023arXiv

citations

Prometheus: 3D-Aware Latent Diffusion Models for Feed-Forward Text-to-3D Scene Generation

CVPR 2025arXiv

citations

NeRFCodec: Neural Feature Compression Meets Neural Radiance Fields for Memory-Efficient Scene Representation

CVPR 2024arXiv

citations

RICO: Regularizing the Unobservable for Indoor Compositional Reconstruction

ICCV 2023arXiv

citations

EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis

CVPR 2025arXiv

citations

VeRi3D: Generative Vertex-based Radiance Fields for 3D Controllable Human Image Synthesis

ICCV 2023arXiv

citations

Painting 3D Nature in 2D: View Synthesis of Natural Scenes From a Single Semantic Mask

CVPR 2023arXiv

citations

A Visual Navigation Perspective for Category-Level Object Pose Estimation

ECCV 2022arXiv

citations

GIFStream: 4D Gaussian-based Immersive Video with Feature Stream

CVPR 2025arXiv

citations

UrbanCAD: Towards Highly Controllable and Photorealistic 3D Vehicles for Urban Scene Simulation

CVPR 2025arXiv

citations

Vivid4D: Improving 4D Reconstruction from Monocular Video by Video Inpainting

ICCV 2025arXiv

citations

REFRAME: Reflective Surface Real-Time Rendering for Mobile Devices

ECCV 2024arXiv

citations

Yiyi Liao

papers (23)

GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis

KiloNeRF: Speeding Up Neural Radiance Fields With Thousands of Tiny MLPs

Shape As Points: A Differentiable Poisson Solver

VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Grids

Towards Unsupervised Learning of Generative Models for 3D Controllable Image Synthesis

HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting

SMD-Nets: Stereo Mixture Density Networks

On the Frequency Bias of Generative Models

Learning Temporally Consistent Video Depth from Video Diffusion Priors

UrbanGIRAFFE: Representing Urban Scenes as Compositional Generative Neural Feature Fields

SteerNeRF: Accelerating NeRF Rendering via Smooth Viewpoint Trajectory

Learning 3D-Aware Image Synthesis With Unknown Pose Distribution

Prometheus: 3D-Aware Latent Diffusion Models for Feed-Forward Text-to-3D Scene Generation

NeRFCodec: Neural Feature Compression Meets Neural Radiance Fields for Memory-Efficient Scene Representation

RICO: Regularizing the Unobservable for Indoor Compositional Reconstruction

EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis

VeRi3D: Generative Vertex-based Radiance Fields for 3D Controllable Human Image Synthesis

Painting 3D Nature in 2D: View Synthesis of Natural Scenes From a Single Semantic Mask

A Visual Navigation Perspective for Category-Level Object Pose Estimation

GIFStream: 4D Gaussian-based Immersive Video with Feature Stream

UrbanCAD: Towards Highly Controllable and Photorealistic 3D Vehicles for Urban Scene Simulation

Vivid4D: Improving 4D Reconstruction from Monocular Video by Video Inpainting

REFRAME: Reflective Surface Real-Time Rendering for Mobile Devices

papers (23)

GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis

KiloNeRF: Speeding Up Neural Radiance Fields With Thousands of Tiny MLPs

Shape As Points: A Differentiable Poisson Solver

VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Grids

Towards Unsupervised Learning of Generative Models for 3D Controllable Image Synthesis

HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting

SMD-Nets: Stereo Mixture Density Networks

On the Frequency Bias of Generative Models

Learning Temporally Consistent Video Depth from Video Diffusion Priors

UrbanGIRAFFE: Representing Urban Scenes as Compositional Generative Neural Feature Fields

SteerNeRF: Accelerating NeRF Rendering via Smooth Viewpoint Trajectory

Learning 3D-Aware Image Synthesis With Unknown Pose Distribution

Prometheus: 3D-Aware Latent Diffusion Models for Feed-Forward Text-to-3D Scene Generation

NeRFCodec: Neural Feature Compression Meets Neural Radiance Fields for Memory-Efficient Scene Representation

RICO: Regularizing the Unobservable for Indoor Compositional Reconstruction

EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis

VeRi3D: Generative Vertex-based Radiance Fields for 3D Controllable Human Image Synthesis

Painting 3D Nature in 2D: View Synthesis of Natural Scenes From a Single Semantic Mask

A Visual Navigation Perspective for Category-Level Object Pose Estimation

GIFStream: 4D Gaussian-based Immersive Video with Feature Stream

UrbanCAD: Towards Highly Controllable and Photorealistic 3D Vehicles for Urban Scene Simulation

Vivid4D: Improving 4D Reconstruction from Monocular Video by Video Inpainting

REFRAME: Reflective Surface Real-Time Rendering for Mobile Devices