Hsin-Ying Lee

papers

2,046

total citations

papers (29)

ReDAL: Region-Based and Diversity-Aware Active Learning for Point Cloud Semantic Segmentation

ICCV 2021arXiv

citations

DisCoScene: Spatially Disentangled Generative Radiance Fields for Controllable 3D-Aware Scene Synthesis

CVPR 2023arXiv

citations

InfiniCity: Infinite-Scale City Synthesis

ICCV 2023arXiv

citations

RetrieveGAN: Image Synthesis via Differentiable Patch Retrieval

ECCV 2020arXiv

citations

Towards Text-guided 3D Scene Composition

CVPR 2024arXiv

citations

3DAvatarGAN: Bridging Domains for Personalized Editable Avatars

CVPR 2023arXiv

citations

Show Me What and Tell Me How: Video Synthesis via Multimodal Conditioning

CVPR 2022arXiv

citations

Exploiting Diffusion Prior for Generalizable Dense Prediction

CVPR 2024arXiv

citations

SceneTex: High-Quality Texture Synthesis for Indoor Scenes via Diffusion Priors

CVPR 2024arXiv

citations

Cross-Modal 3D Shape Generation and Manipulation

ECCV 2022arXiv

citations

Semantic View Synthesis

ECCV 2020arXiv

citations

Vector Quantized Image-to-Image Translation

ECCV 2022arXiv

citations

Controllable Image Synthesis via SegVAE

ECCV 2020arXiv

citations

Unsupervised Volumetric Animation

CVPR 2023arXiv

citations

4Real-Video: Learning Generalizable Photo-Realistic 4D Video Diffusion

CVPR 2025arXiv

citations

PrEditor3D: Fast and Precise 3D Shape Editing

CVPR 2025arXiv

citations

UpFusion: Novel View Diffusion from Unposed Sparse View Observations

ECCV 2024arXiv

citations

D2ADA: Dynamic Density-Aware Active Domain Adaptation for Semantic Segmentation

ECCV 2022arXiv

citations

GTR: Improving Large 3D Reconstruction Models through Geometry and Texture Refinement

ICLR 2025arXiv

citations

UniPhy: Learning a Unified Constitutive Model for Inverse Physics Simulation

CVPR 2025arXiv

citations

T2Bs: Text-to-Character Blendshapes via Video Generation

ICCV 2025arXiv

citations

Exploring Cross-Video and Cross-Modality Signals for Weakly-Supervised Audio-Visual Video Parsing

NEURIPS 2021

citations

InOut: Diverse Image Outpainting via GAN Inversion

CVPR 2022

citations

Hsin-Ying Lee

papers (29)

Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers

SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generation

Text2Tex: Text-driven Texture Synthesis via Diffusion Models

Neural Design Network: Graphic Layout Generation with Constraints

VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control

Make-a-Story: Visual Memory Conditioned Consistent Story Generation

ReDAL: Region-Based and Diversity-Aware Active Learning for Point Cloud Semantic Segmentation

DisCoScene: Spatially Disentangled Generative Radiance Fields for Controllable 3D-Aware Scene Synthesis

InfiniCity: Infinite-Scale City Synthesis

RetrieveGAN: Image Synthesis via Differentiable Patch Retrieval

Towards Text-guided 3D Scene Composition

3DAvatarGAN: Bridging Domains for Personalized Editable Avatars

Show Me What and Tell Me How: Video Synthesis via Multimodal Conditioning

Exploiting Diffusion Prior for Generalizable Dense Prediction

SceneTex: High-Quality Texture Synthesis for Indoor Scenes via Diffusion Priors

Cross-Modal 3D Shape Generation and Manipulation

Semantic View Synthesis

Vector Quantized Image-to-Image Translation

Controllable Image Synthesis via SegVAE

Unsupervised Volumetric Animation

4Real-Video: Learning Generalizable Photo-Realistic 4D Video Diffusion

PrEditor3D: Fast and Precise 3D Shape Editing

UpFusion: Novel View Diffusion from Unposed Sparse View Observations

D2ADA: Dynamic Density-Aware Active Domain Adaptation for Semantic Segmentation

GTR: Improving Large 3D Reconstruction Models through Geometry and Texture Refinement

UniPhy: Learning a Unified Constitutive Model for Inverse Physics Simulation

T2Bs: Text-to-Character Blendshapes via Video Generation

Exploring Cross-Video and Cross-Modality Signals for Weakly-Supervised Audio-Visual Video Parsing

InOut: Diverse Image Outpainting via GAN Inversion

papers (29)

Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers

SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generation

Text2Tex: Text-driven Texture Synthesis via Diffusion Models

Neural Design Network: Graphic Layout Generation with Constraints

VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control

Make-a-Story: Visual Memory Conditioned Consistent Story Generation

ReDAL: Region-Based and Diversity-Aware Active Learning for Point Cloud Semantic Segmentation

DisCoScene: Spatially Disentangled Generative Radiance Fields for Controllable 3D-Aware Scene Synthesis

InfiniCity: Infinite-Scale City Synthesis

RetrieveGAN: Image Synthesis via Differentiable Patch Retrieval

Towards Text-guided 3D Scene Composition

3DAvatarGAN: Bridging Domains for Personalized Editable Avatars

Show Me What and Tell Me How: Video Synthesis via Multimodal Conditioning

Exploiting Diffusion Prior for Generalizable Dense Prediction

SceneTex: High-Quality Texture Synthesis for Indoor Scenes via Diffusion Priors

Cross-Modal 3D Shape Generation and Manipulation

Semantic View Synthesis

Vector Quantized Image-to-Image Translation

Controllable Image Synthesis via SegVAE

Unsupervised Volumetric Animation

4Real-Video: Learning Generalizable Photo-Realistic 4D Video Diffusion

PrEditor3D: Fast and Precise 3D Shape Editing

UpFusion: Novel View Diffusion from Unposed Sparse View Observations

D2ADA: Dynamic Density-Aware Active Domain Adaptation for Semantic Segmentation

GTR: Improving Large 3D Reconstruction Models through Geometry and Texture Refinement

UniPhy: Learning a Unified Constitutive Model for Inverse Physics Simulation

T2Bs: Text-to-Character Blendshapes via Video Generation

Exploring Cross-Video and Cross-Modality Signals for Weakly-Supervised Audio-Visual Video Parsing

InOut: Diverse Image Outpainting via GAN Inversion