Xiaodong Gu

Affiliations

Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong

papers

1,455

total citations

papers (15)

Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching

CVPR 2020arXiv

872

citations

Neural Window Fully-Connected CRFs for Monocular Depth Estimation

CVPR 2022arXiv

254

citations

RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D

CVPR 2024arXiv

173

citations

UTC: A Unified Transformer With Inter-Task Contrastive Learning for Visual Dialog

CVPR 2022arXiv

citations

LaMP: Language-Motion Pretraining for Motion Generation, Retrieval, and Captioning

ICLR 2025arXiv

citations

MMRL: Multi-Modal Representation Learning for Vision-Language Models

CVPR 2025arXiv

citations

AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstruction

CVPR 2025arXiv

citations

GenS: Generalizable Neural Surface Reconstruction from Multi-View Images

NEURIPS 2023arXiv

citations

Surface-Centric Modeling for High-Fidelity Generalizable Neural Surface Reconstruction

ECCV 2024arXiv

citations

An Optimization Framework to Enforce Multi-View Consistency for Texturing 3D Meshes

ECCV 2024arXiv

citations

GPLD3D: Latent Diffusion of 3D Shape Generative Models by Enforcing Geometric and Physical Priors

CVPR 2024

citations

LHM: Large Animatable Human Reconstruction Model for Single Image to 3D in Seconds

ICCV 2025

citations

Xiaodong Gu

Affiliations

papers (15)

Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching

Neural Window Fully-Connected CRFs for Monocular Depth Estimation

RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D

UTC: A Unified Transformer With Inter-Task Contrastive Learning for Visual Dialog

LaMP: Language-Motion Pretraining for Motion Generation, Retrieval, and Captioning

MMRL: Multi-Modal Representation Learning for Vision-Language Models

AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstruction

GenS: Generalizable Neural Surface Reconstruction from Multi-View Images

Surface-Centric Modeling for High-Fidelity Generalizable Neural Surface Reconstruction

An Optimization Framework to Enforce Multi-View Consistency for Texturing 3D Meshes

JoAPR: Cleaning the Lens of Prompt Learning for Vision-Language Models

Motions as Queries: One-Stage Multi-Person Holistic Human Motion Capture

RCP: Recurrent Closest Point for Point Cloud

GPLD3D: Latent Diffusion of 3D Shape Generative Models by Enforcing Geometric and Physical Priors

LHM: Large Animatable Human Reconstruction Model for Single Image to 3D in Seconds

papers (15)

Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching

Neural Window Fully-Connected CRFs for Monocular Depth Estimation

RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D

UTC: A Unified Transformer With Inter-Task Contrastive Learning for Visual Dialog

LaMP: Language-Motion Pretraining for Motion Generation, Retrieval, and Captioning

MMRL: Multi-Modal Representation Learning for Vision-Language Models

AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstruction

GenS: Generalizable Neural Surface Reconstruction from Multi-View Images

Surface-Centric Modeling for High-Fidelity Generalizable Neural Surface Reconstruction

An Optimization Framework to Enforce Multi-View Consistency for Texturing 3D Meshes

JoAPR: Cleaning the Lens of Prompt Learning for Vision-Language Models

Motions as Queries: One-Stage Multi-Person Holistic Human Motion Capture

RCP: Recurrent Closest Point for Point Cloud

GPLD3D: Latent Diffusion of 3D Shape Generative Models by Enforcing Geometric and Physical Priors

LHM: Large Animatable Human Reconstruction Model for Single Image to 3D in Seconds