Jun Gao

22

Papers

222

Total Citations

Papers (22)

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

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

Interleaved-Modal Chain-of-Thought

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

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

Fast Interactive Object Annotation With Curve-GCN

DatasetGAN: Efficient Labeled Data Factory With Minimal Human Effort

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

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

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

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

ScribbleBox: Interactive Annotation Framework for Video Object Segmentation

Interactive Annotation of 3D Object Geometry using 2D Scribbles

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

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

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

Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer

Learning Deformable Tetrahedral Meshes for 3D Reconstruction

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

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

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

Dropout Training, Data-dependent Regularization, and Generalization Bounds