Hao Xu

papers

458

total citations

papers (19)

OMNet: Learning Overlapping Mask for Partial-to-Partial Point Cloud Registration

ICCV 2021arXiv

188

citations

EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation

ICCV 2023arXiv

173

citations

D-IF: Uncertainty-aware Human Digitization via Implicit Distribution Field

ICCV 2023arXiv

citations

HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactions

CVPR 2024arXiv

citations

Open-Vocabulary 3D Semantic Segmentation with Text-to-Image Diffusion Models

ECCV 2024arXiv

citations

TACIT: A Target-Agnostic Feature Disentanglement Framework for Cross-Domain Text Classification

AAAI 2024arXiv

citations

Multirate Neural Image Compression with Adaptive Lattice Vector Quantization

CVPR 2025

citations

AdsQA: Towards Advertisement Video Understanding

ICCV 2025arXiv

citations

SiMA-Hand: Boosting 3D Hand-Mesh Reconstruction by Single-to-Multi-View Adaptation

AAAI 2024arXiv

citations

Deciphering Compatibility Relationships with Textual Descriptions via Extraction and Explanation

AAAI 2024arXiv

citations

UN-DETR: Promoting Objectness Learning via Joint Supervision for Unknown Object Detection

AAAI 2025arXiv

citations

UniHOPE: A Unified Approach for Hand-Only and Hand-Object Pose Estimation

CVPR 2025arXiv

citations

SIRA-PCR: Sim-to-Real Adaptation for 3D Point Cloud Registration

ICCV 2023

citations

H2ONet: Hand-Occlusion-and-Orientation-Aware Network for Real-Time 3D Hand Mesh Reconstruction

CVPR 2023

citations

How Do Position Encodings Affect Length Generalization? Case Studies On In-Context Function Learning

AAAI 2025

citations

HybridReg: Robust 3D Point Cloud Registration with Hybrid Motions

AAAI 2025arXiv

citations

Hao Xu

papers (19)

OMNet: Learning Overlapping Mask for Partial-to-Partial Point Cloud Registration

EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation

D-IF: Uncertainty-aware Human Digitization via Implicit Distribution Field

HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactions

Open-Vocabulary 3D Semantic Segmentation with Text-to-Image Diffusion Models

TACIT: A Target-Agnostic Feature Disentanglement Framework for Cross-Domain Text Classification

Multirate Neural Image Compression with Adaptive Lattice Vector Quantization

AdsQA: Towards Advertisement Video Understanding

SiMA-Hand: Boosting 3D Hand-Mesh Reconstruction by Single-to-Multi-View Adaptation

Deciphering Compatibility Relationships with Textual Descriptions via Extraction and Explanation

UN-DETR: Promoting Objectness Learning via Joint Supervision for Unknown Object Detection

UniHOPE: A Unified Approach for Hand-Only and Hand-Object Pose Estimation

SIRA-PCR: Sim-to-Real Adaptation for 3D Point Cloud Registration

H2ONet: Hand-Occlusion-and-Orientation-Aware Network for Real-Time 3D Hand Mesh Reconstruction

Embodied Representation Alignment with Mirror Neurons

Simulating Dual-Pixel Images From Ray Tracing For Depth Estimation

FCC: Feature Clusters Compression for Long-Tailed Visual Recognition

How Do Position Encodings Affect Length Generalization? Case Studies On In-Context Function Learning

HybridReg: Robust 3D Point Cloud Registration with Hybrid Motions

papers (19)

OMNet: Learning Overlapping Mask for Partial-to-Partial Point Cloud Registration

EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation

D-IF: Uncertainty-aware Human Digitization via Implicit Distribution Field

HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactions

Open-Vocabulary 3D Semantic Segmentation with Text-to-Image Diffusion Models

TACIT: A Target-Agnostic Feature Disentanglement Framework for Cross-Domain Text Classification

Multirate Neural Image Compression with Adaptive Lattice Vector Quantization

AdsQA: Towards Advertisement Video Understanding

SiMA-Hand: Boosting 3D Hand-Mesh Reconstruction by Single-to-Multi-View Adaptation

Deciphering Compatibility Relationships with Textual Descriptions via Extraction and Explanation

UN-DETR: Promoting Objectness Learning via Joint Supervision for Unknown Object Detection

UniHOPE: A Unified Approach for Hand-Only and Hand-Object Pose Estimation

SIRA-PCR: Sim-to-Real Adaptation for 3D Point Cloud Registration

H2ONet: Hand-Occlusion-and-Orientation-Aware Network for Real-Time 3D Hand Mesh Reconstruction

Embodied Representation Alignment with Mirror Neurons

Simulating Dual-Pixel Images From Ray Tracing For Depth Estimation

FCC: Feature Clusters Compression for Long-Tailed Visual Recognition

How Do Position Encodings Affect Length Generalization? Case Studies On In-Context Function Learning

HybridReg: Robust 3D Point Cloud Registration with Hybrid Motions