Zhiyang Dou

Affiliations

The University of Hong Kong

papers

1,078

total citations

papers (19)

Wonder3D: Single Image to 3D using Cross-Domain Diffusion

CVPR 2024arXiv

672

citations

TLControl: Trajectory and Language Control for Human Motion Synthesis

ECCV 2024arXiv

citations

EMDM: Efficient Motion Diffusion Model for Fast, High-Quality Human Motion Generation

ECCV 2024

citations

Align3R: Aligned Monocular Depth Estimation for Dynamic Videos

CVPR 2025arXiv

citations

TORE: Token Reduction for Efficient Human Mesh Recovery with Transformer

ICCV 2023arXiv

citations

TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization

CVPR 2025arXiv

citations

PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation

NEURIPS 2025arXiv

citations

Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Models

ECCV 2024arXiv

citations

ModSkill: Physical Character Skill Modularization

ICCV 2025arXiv

citations

CityAnchor: City-scale 3D Visual Grounding with Multi-modality LLMs

ICLR 2025

citations

Vid2Sim: Generalizable, Video-based Reconstruction of Appearance, Geometry and Physics for Mesh-free Simulation

CVPR 2025arXiv

citations

🎧MOSPA: Human Motion Generation Driven by Spatial Audio

NEURIPS 2025arXiv

citations

SIMS: Simulating Stylized Human-Scene Interactions with Retrieval-Augmented Script Generation

ICCV 2025arXiv

citations

CoDA: Coordinated Diffusion Noise Optimization for Whole-Body Manipulation of Articulated Objects

NEURIPS 2025arXiv

citations

SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction

NEURIPS 2025arXiv

citations

TrackingWorld: World-centric Monocular 3D Tracking of Almost All Pixels

NEURIPS 2025arXiv

citations

Zhiyang Dou

Affiliations

papers (19)

Wonder3D: Single Image to 3D using Cross-Domain Diffusion

TLControl: Trajectory and Language Control for Human Motion Synthesis

EMDM: Efficient Motion Diffusion Model for Fast, High-Quality Human Motion Generation

Align3R: Aligned Monocular Depth Estimation for Dynamic Videos

TORE: Token Reduction for Efficient Human Mesh Recovery with Transformer

TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization

ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Model

Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data

Boosting Segment Anything Model Towards Open-Vocabulary Learning

PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation

Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Models

ModSkill: Physical Character Skill Modularization

CityAnchor: City-scale 3D Visual Grounding with Multi-modality LLMs

Vid2Sim: Generalizable, Video-based Reconstruction of Appearance, Geometry and Physics for Mesh-free Simulation

🎧MOSPA: Human Motion Generation Driven by Spatial Audio

SIMS: Simulating Stylized Human-Scene Interactions with Retrieval-Augmented Script Generation

CoDA: Coordinated Diffusion Noise Optimization for Whole-Body Manipulation of Articulated Objects

SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction

TrackingWorld: World-centric Monocular 3D Tracking of Almost All Pixels

papers (19)

Wonder3D: Single Image to 3D using Cross-Domain Diffusion

TLControl: Trajectory and Language Control for Human Motion Synthesis

EMDM: Efficient Motion Diffusion Model for Fast, High-Quality Human Motion Generation

Align3R: Aligned Monocular Depth Estimation for Dynamic Videos

TORE: Token Reduction for Efficient Human Mesh Recovery with Transformer

TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization

ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Model

Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data

Boosting Segment Anything Model Towards Open-Vocabulary Learning

PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation

Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Models

ModSkill: Physical Character Skill Modularization

CityAnchor: City-scale 3D Visual Grounding with Multi-modality LLMs

Vid2Sim: Generalizable, Video-based Reconstruction of Appearance, Geometry and Physics for Mesh-free Simulation

🎧MOSPA: Human Motion Generation Driven by Spatial Audio

SIMS: Simulating Stylized Human-Scene Interactions with Retrieval-Augmented Script Generation

CoDA: Coordinated Diffusion Noise Optimization for Whole-Body Manipulation of Articulated Objects

SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction

TrackingWorld: World-centric Monocular 3D Tracking of Almost All Pixels