Yu-Kun Lai

papers

1,370

total citations

papers (27)

StylizedNeRF: Consistent 3D Scene Stylization As Stylized NeRF via 2D-3D Mutual Learning

CVPR 2022arXiv

177

citations

PISE: Person Image Synthesis and Editing With Decoupled GAN

CVPR 2021arXiv

131

citations

Towards Artistic Image Aesthetics Assessment: A Large-Scale Dataset and a New Method

CVPR 2023arXiv

citations

Manifold Alignment for Semantically Aligned Style Transfer

ICCV 2021arXiv

citations

FOF: Learning Fourier Occupancy Field for Monocular Real-time Human Reconstruction

NEURIPS 2022arXiv

citations

CXTrack: Improving 3D Point Cloud Tracking With Contextual Information

CVPR 2023arXiv

citations

Texture-GS: Disentangle the Geometry and Texture for 3D Gaussian Splatting Editing

ECCV 2024arXiv

citations

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

ICCV 2023arXiv

citations

Real-time 3D-aware Portrait Video Relighting

CVPR 2024arXiv

citations

SuperSVG: Superpixel-based Scalable Vector Graphics Synthesis

CVPR 2024arXiv

citations

Crowd3D: Towards Hundreds of People Reconstruction From a Single Image

CVPR 2023arXiv

citations

RESCUE: Crowd Evacuation Simulation via Controlling SDM-United Characters

ICCV 2025arXiv

citations

E3Sym: Leveraging E(3) Invariance for Unsupervised 3D Planar Reflective Symmetry Detection

ICCV 2023

citations

Hierarchical Layout-Aware Graph Convolutional Network for Unified Aesthetics Assessment

CVPR 2021

citations

MLVSNet: Multi-Level Voting Siamese Network for 3D Visual Tracking

ICCV 2021

citations

Single Image 3D Shape Retrieval via Cross-Modal Instance and Category Contrastive Learning

ICCV 2021

citations

High-Fidelity Human Avatars From a Single RGB Camera

CVPR 2022

citations

Learning Semantic-Aware Disentangled Representation for Flexible 3D Human Body Editing

CVPR 2023

citations

Feature Proliferation -- the "Cancer" in StyleGAN and its Treatments

ICCV 2023

citations

Unpaired Portrait Drawing Generation via Asymmetric Cycle Mapping

CVPR 2020

citations

Efficient Precision and Recall Metrics for Assessing Generative Models using Hubness-aware Sampling

ICML 2024

citations

LGA-Net: Learning Local and Global Affinities for Sparse Scribble based Image Colorization

ICCV 2025

citations

SceneSketcher: Fine-Grained Image Retrieval with Scene Sketches

ECCV 2020

citations

VENet: Voting Enhancement Network for 3D Object Detection

ICCV 2021

citations

Yu-Kun Lai

papers (27)

NeRF-Editing: Geometry Editing of Neural Radiance Fields

BBDM: Image-to-Image Translation With Brownian Bridge Diffusion Models

MLCVNet: Multi-Level Context VoteNet for 3D Object Detection

StylizedNeRF: Consistent 3D Scene Stylization As Stylized NeRF via 2D-3D Mutual Learning

PISE: Person Image Synthesis and Editing With Decoupled GAN

Towards Artistic Image Aesthetics Assessment: A Large-Scale Dataset and a New Method

Manifold Alignment for Semantically Aligned Style Transfer

FOF: Learning Fourier Occupancy Field for Monocular Real-time Human Reconstruction

CXTrack: Improving 3D Point Cloud Tracking With Contextual Information

Texture-GS: Disentangle the Geometry and Texture for 3D Gaussian Splatting Editing

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

Real-time 3D-aware Portrait Video Relighting

SuperSVG: Superpixel-based Scalable Vector Graphics Synthesis

Crowd3D: Towards Hundreds of People Reconstruction From a Single Image

RESCUE: Crowd Evacuation Simulation via Controlling SDM-United Characters

E3Sym: Leveraging E(3) Invariance for Unsupervised 3D Planar Reflective Symmetry Detection

Hierarchical Layout-Aware Graph Convolutional Network for Unified Aesthetics Assessment

MLVSNet: Multi-Level Voting Siamese Network for 3D Visual Tracking

Single Image 3D Shape Retrieval via Cross-Modal Instance and Category Contrastive Learning

High-Fidelity Human Avatars From a Single RGB Camera

Learning Semantic-Aware Disentangled Representation for Flexible 3D Human Body Editing

Feature Proliferation -- the "Cancer" in StyleGAN and its Treatments

Unpaired Portrait Drawing Generation via Asymmetric Cycle Mapping

Efficient Precision and Recall Metrics for Assessing Generative Models using Hubness-aware Sampling

LGA-Net: Learning Local and Global Affinities for Sparse Scribble based Image Colorization

SceneSketcher: Fine-Grained Image Retrieval with Scene Sketches

VENet: Voting Enhancement Network for 3D Object Detection

papers (27)

NeRF-Editing: Geometry Editing of Neural Radiance Fields

BBDM: Image-to-Image Translation With Brownian Bridge Diffusion Models

MLCVNet: Multi-Level Context VoteNet for 3D Object Detection

StylizedNeRF: Consistent 3D Scene Stylization As Stylized NeRF via 2D-3D Mutual Learning

PISE: Person Image Synthesis and Editing With Decoupled GAN

Towards Artistic Image Aesthetics Assessment: A Large-Scale Dataset and a New Method

Manifold Alignment for Semantically Aligned Style Transfer

FOF: Learning Fourier Occupancy Field for Monocular Real-time Human Reconstruction

CXTrack: Improving 3D Point Cloud Tracking With Contextual Information

Texture-GS: Disentangle the Geometry and Texture for 3D Gaussian Splatting Editing

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

Real-time 3D-aware Portrait Video Relighting

SuperSVG: Superpixel-based Scalable Vector Graphics Synthesis

Crowd3D: Towards Hundreds of People Reconstruction From a Single Image

RESCUE: Crowd Evacuation Simulation via Controlling SDM-United Characters

E3Sym: Leveraging E(3) Invariance for Unsupervised 3D Planar Reflective Symmetry Detection

Hierarchical Layout-Aware Graph Convolutional Network for Unified Aesthetics Assessment

MLVSNet: Multi-Level Voting Siamese Network for 3D Visual Tracking

Single Image 3D Shape Retrieval via Cross-Modal Instance and Category Contrastive Learning

High-Fidelity Human Avatars From a Single RGB Camera

Learning Semantic-Aware Disentangled Representation for Flexible 3D Human Body Editing

Feature Proliferation -- the "Cancer" in StyleGAN and its Treatments

Unpaired Portrait Drawing Generation via Asymmetric Cycle Mapping

Efficient Precision and Recall Metrics for Assessing Generative Models using Hubness-aware Sampling

LGA-Net: Learning Local and Global Affinities for Sparse Scribble based Image Colorization

SceneSketcher: Fine-Grained Image Retrieval with Scene Sketches

VENet: Voting Enhancement Network for 3D Object Detection