Xiaoyang Wu

papers

1,312

total citations

papers (16)

Point Transformer V2: Grouped Vector Attention and Partition-based Pooling

NEURIPS 2022arXiv

629

citations

Hierarchical Dense Correlation Distillation for Few-Shot Segmentation

CVPR 2023arXiv

137

citations

Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training

CVPR 2024arXiv

citations

Masked Scene Contrast: A Scalable Framework for Unsupervised 3D Representation Learning

CVPR 2023arXiv

citations

Sonata: Self-Supervised Learning of Reliable Point Representations

CVPR 2025arXiv

citations

Multi-Space Alignments Towards Universal LiDAR Segmentation

CVPR 2024arXiv

citations

MarS3D: A Plug-and-Play Motion-Aware Model for Semantic Segmentation on Multi-Scan 3D Point Clouds

CVPR 2023arXiv

citations

GroupContrast: Semantic-aware Self-supervised Representation Learning for 3D Understanding

CVPR 2024arXiv

citations

DreamComposer: Controllable 3D Object Generation via Multi-View Conditions

CVPR 2024arXiv

citations

LiteReality: Graphic-Ready 3D Scene Reconstruction from RGB-D Scans

NEURIPS 2025arXiv

citations

MiCo: Multi-image Contrast for Reinforcement Visual Reasoning

NEURIPS 2025arXiv

citations

Point Transformer V3: Simpler Faster Stronger

CVPR 2024

citations

Xiaoyang Wu

papers (16)

Point Transformer V2: Grouped Vector Attention and Partition-based Pooling

Hierarchical Dense Correlation Distillation for Few-Shot Segmentation

Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training

UniPAD: A Universal Pre-training Paradigm for Autonomous Driving

Understanding Imbalanced Semantic Segmentation Through Neural Collapse

GPT4Point: A Unified Framework for Point-Language Understanding and Generation

OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation

Masked Scene Contrast: A Scalable Framework for Unsupervised 3D Representation Learning

Sonata: Self-Supervised Learning of Reliable Point Representations

Multi-Space Alignments Towards Universal LiDAR Segmentation

MarS3D: A Plug-and-Play Motion-Aware Model for Semantic Segmentation on Multi-Scan 3D Point Clouds

GroupContrast: Semantic-aware Self-supervised Representation Learning for 3D Understanding

DreamComposer: Controllable 3D Object Generation via Multi-View Conditions

LiteReality: Graphic-Ready 3D Scene Reconstruction from RGB-D Scans

MiCo: Multi-image Contrast for Reinforcement Visual Reasoning

Point Transformer V3: Simpler Faster Stronger

papers (16)

Point Transformer V2: Grouped Vector Attention and Partition-based Pooling

Hierarchical Dense Correlation Distillation for Few-Shot Segmentation

Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training

UniPAD: A Universal Pre-training Paradigm for Autonomous Driving

Understanding Imbalanced Semantic Segmentation Through Neural Collapse

GPT4Point: A Unified Framework for Point-Language Understanding and Generation

OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation

Masked Scene Contrast: A Scalable Framework for Unsupervised 3D Representation Learning

Sonata: Self-Supervised Learning of Reliable Point Representations

Multi-Space Alignments Towards Universal LiDAR Segmentation

MarS3D: A Plug-and-Play Motion-Aware Model for Semantic Segmentation on Multi-Scan 3D Point Clouds

GroupContrast: Semantic-aware Self-supervised Representation Learning for 3D Understanding

DreamComposer: Controllable 3D Object Generation via Multi-View Conditions

LiteReality: Graphic-Ready 3D Scene Reconstruction from RGB-D Scans

MiCo: Multi-image Contrast for Reinforcement Visual Reasoning

Point Transformer V3: Simpler Faster Stronger