Hong-Xing Yu

papers

1,094

total citations

papers (21)

Digital Twin Catalog: A Large-Scale Photorealistic 3D Object Digital Twin Dataset

CVPR 2025arXiv

citations

Weakly Supervised Discriminative Feature Learning With State Information for Person Identification

CVPR 2020arXiv

citations

Are These the Same Apple? Comparing Images Based on Object Intrinsics

NEURIPS 2023arXiv

citations

3D Copy-Paste: Physically Plausible Object Insertion for Monocular 3D Detection

NEURIPS 2023arXiv

citations

WonderPlay: Dynamic 3D Scene Generation from a Single Image and Actions

ICCV 2025arXiv

citations

BEHAVIOR Vision Suite: Customizable Dataset Generation via Simulation

CVPR 2024arXiv

citations

FluidNexus: 3D Fluid Reconstruction and Prediction from a Single Video

CVPR 2025arXiv

citations

Accidental Light Probes

CVPR 2023arXiv

citations

Multi-Object Manipulation via Object-Centric Neural Scattering Functions

CVPR 2023arXiv

citations

Tree-Structured Shading Decomposition

ICCV 2023arXiv

citations

Seeing the Wind from a Falling Leaf

NEURIPS 2025arXiv

citations

OpenRooms: An Open Framework for Photorealistic Indoor Scene Datasets

CVPR 2021

citations

Hong-Xing Yu

papers (21)

Neural Radiance Flow for 4D View Synthesis and Video Processing

Physics-Based Interaction with 3D Objects via Video Generation

WonderWorld: Interactive 3D Scene Generation from a Single Image

WonderJourney: Going from Anywhere to Everywhere

ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Image

Stanford-ORB: A Real-World 3D Object Inverse Rendering Benchmark

WorldScore: Unified Evaluation Benchmark for World Generation

Rotationally Equivariant 3D Object Detection

Inferring Hybrid Neural Fluid Fields from Videos

Digital Twin Catalog: A Large-Scale Photorealistic 3D Object Digital Twin Dataset

Weakly Supervised Discriminative Feature Learning With State Information for Person Identification

Are These the Same Apple? Comparing Images Based on Object Intrinsics

3D Copy-Paste: Physically Plausible Object Insertion for Monocular 3D Detection

WonderPlay: Dynamic 3D Scene Generation from a Single Image and Actions

BEHAVIOR Vision Suite: Customizable Dataset Generation via Simulation

FluidNexus: 3D Fluid Reconstruction and Prediction from a Single Video

Accidental Light Probes

Multi-Object Manipulation via Object-Centric Neural Scattering Functions

Tree-Structured Shading Decomposition

Seeing the Wind from a Falling Leaf

OpenRooms: An Open Framework for Photorealistic Indoor Scene Datasets

papers (21)

Neural Radiance Flow for 4D View Synthesis and Video Processing

Physics-Based Interaction with 3D Objects via Video Generation

WonderWorld: Interactive 3D Scene Generation from a Single Image

WonderJourney: Going from Anywhere to Everywhere

ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Image

Stanford-ORB: A Real-World 3D Object Inverse Rendering Benchmark

WorldScore: Unified Evaluation Benchmark for World Generation

Rotationally Equivariant 3D Object Detection

Inferring Hybrid Neural Fluid Fields from Videos

Digital Twin Catalog: A Large-Scale Photorealistic 3D Object Digital Twin Dataset

Weakly Supervised Discriminative Feature Learning With State Information for Person Identification

Are These the Same Apple? Comparing Images Based on Object Intrinsics

3D Copy-Paste: Physically Plausible Object Insertion for Monocular 3D Detection

WonderPlay: Dynamic 3D Scene Generation from a Single Image and Actions

BEHAVIOR Vision Suite: Customizable Dataset Generation via Simulation

FluidNexus: 3D Fluid Reconstruction and Prediction from a Single Video

Accidental Light Probes

Multi-Object Manipulation via Object-Centric Neural Scattering Functions

Tree-Structured Shading Decomposition

Seeing the Wind from a Falling Leaf

OpenRooms: An Open Framework for Photorealistic Indoor Scene Datasets