Jun Gao

Affiliations

University of Toronto

papers

4,250

total citations

papers (20)

Magic3D: High-Resolution Text-to-3D Content Creation

CVPR 2023arXiv

1,461

citations

Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesis

NEURIPS 2021arXiv

580

citations

GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images

NEURIPS 2022arXiv

564

citations

Extracting Triangular 3D Models, Materials, and Lighting From Images

CVPR 2022arXiv

461

citations

DatasetGAN: Efficient Labeled Data Factory With Minimal Human Effort

CVPR 2021arXiv

378

citations

GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control

CVPR 2025arXiv

144

citations

Learning Deformable Tetrahedral Meshes for 3D Reconstruction

NEURIPS 2020arXiv

120

citations

Neural Fields Meet Explicit Geometric Representations for Inverse Rendering of Urban Scenes

CVPR 2023arXiv

113

citations

3DStyleNet: Creating 3D Shapes With Geometric and Texture Style Variations

ICCV 2021arXiv

citations

DIB-R++: Learning to Predict Lighting and Material with a Hybrid Differentiable Renderer

NEURIPS 2021arXiv

citations

DIFIX3D+: Improving 3D Reconstructions with Single-Step Diffusion Models

CVPR 2025arXiv

citations

PartField: Learning 3D Feature Fields for Part Segmentation and Beyond

ICCV 2025arXiv

citations

InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models

ICCV 2025arXiv

citations

Diffusion Renderer: Neural Inverse and Forward Rendering with Video Diffusion Models

CVPR 2025

citations

Beyond Fixed Grid: Learning Geometric Image Representation with a Deformable Grid

ECCV 2020arXiv

citations

AIM: Let Any Multimodal Large Language Models Embrace Efficient In-Context Learning

AAAI 2025

citations

Jun Gao

Affiliations

papers (20)

Magic3D: High-Resolution Text-to-3D Content Creation

Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesis

GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images

Extracting Triangular 3D Models, Materials, and Lighting From Images

DatasetGAN: Efficient Labeled Data Factory With Minimal Human Effort

GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control

Learning Deformable Tetrahedral Meshes for 3D Reconstruction

Neural Fields Meet Explicit Geometric Representations for Inverse Rendering of Urban Scenes

3DStyleNet: Creating 3D Shapes With Geometric and Texture Style Variations

DIB-R++: Learning to Predict Lighting and Material with a Hybrid Differentiable Renderer

DIFIX3D+: Improving 3D Reconstructions with Single-Step Diffusion Models

PartField: Learning 3D Feature Fields for Part Segmentation and Beyond

InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models

Diffusion Renderer: Neural Inverse and Forward Rendering with Video Diffusion Models

Beyond Fixed Grid: Learning Geometric Image Representation with a Deformable Grid

Interleaved-Modal Chain-of-Thought

ScribbleBox: Interactive Annotation Framework for Video Object Segmentation

Interactive Annotation of 3D Object Geometry using 2D Scribbles

WildFusion: Learning 3D-Aware Latent Diffusion Models in View Space

AIM: Let Any Multimodal Large Language Models Embrace Efficient In-Context Learning

papers (20)

Magic3D: High-Resolution Text-to-3D Content Creation

Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesis

GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images

Extracting Triangular 3D Models, Materials, and Lighting From Images

DatasetGAN: Efficient Labeled Data Factory With Minimal Human Effort

GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control

Learning Deformable Tetrahedral Meshes for 3D Reconstruction

Neural Fields Meet Explicit Geometric Representations for Inverse Rendering of Urban Scenes

3DStyleNet: Creating 3D Shapes With Geometric and Texture Style Variations

DIB-R++: Learning to Predict Lighting and Material with a Hybrid Differentiable Renderer

DIFIX3D+: Improving 3D Reconstructions with Single-Step Diffusion Models

PartField: Learning 3D Feature Fields for Part Segmentation and Beyond

InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models

Diffusion Renderer: Neural Inverse and Forward Rendering with Video Diffusion Models

Beyond Fixed Grid: Learning Geometric Image Representation with a Deformable Grid

Interleaved-Modal Chain-of-Thought

ScribbleBox: Interactive Annotation Framework for Video Object Segmentation

Interactive Annotation of 3D Object Geometry using 2D Scribbles

WildFusion: Learning 3D-Aware Latent Diffusion Models in View Space

AIM: Let Any Multimodal Large Language Models Embrace Efficient In-Context Learning