Lei Zhou

papers

2,896

total citations

papers (18)

Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware Multi-view Geometry Consistency

ECCV 2020arXiv

154

citations

Learning To Match Features With Seeded Graph Matching Network

ICCV 2021arXiv

150

citations

Goal-Oriented Gaze Estimation for Zero-Shot Learning

CVPR 2021arXiv

149

citations

Joint Semantic Segmentation and Boundary Detection Using Iterative Pyramid Contexts

CVPR 2020arXiv

139

citations

KFNet: Learning Temporal Camera Relocalization Using Kalman Filtering

CVPR 2020arXiv

citations

Learning Discriminative Feature with CRF for Unsupervised Video Object Segmentation

ECCV 2020arXiv

citations

Stochastic Bundle Adjustment for Efficient and Scalable 3D Reconstruction

ECCV 2020arXiv

citations

GasMono: Geometry-Aided Self-Supervised Monocular Depth Estimation for Indoor Scenes

ICCV 2023arXiv

citations

UniGraspTransformer: Simplified Policy Distillation for Scalable Dexterous Robotic Grasping

CVPR 2025arXiv

citations

ROS-SAM: High-Quality Interactive Segmentation for Remote Sensing Moving Object

CVPR 2025arXiv

citations

OxyGenerator: Reconstructing Global Ocean Deoxygenation Over a Century with Deep Learning

ICML 2024arXiv

citations

Learning Visual Proxy for Compositional Zero-Shot Learning

ICCV 2025arXiv

citations

Where to Focus: Investigating Hierarchical Attention Relationship for Fine-Grained Visual Classification

ECCV 2022

citations

Lei Zhou

papers (18)

BlendedMVS: A Large-Scale Dataset for Generalized Multi-View Stereo Networks

D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features

PointDSC: Robust Point Cloud Registration Using Deep Spatial Consistency

ASLFeat: Learning Local Features of Accurate Shape and Localization

ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer

Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware Multi-view Geometry Consistency

Learning To Match Features With Seeded Graph Matching Network

Goal-Oriented Gaze Estimation for Zero-Shot Learning

Joint Semantic Segmentation and Boundary Detection Using Iterative Pyramid Contexts

KFNet: Learning Temporal Camera Relocalization Using Kalman Filtering

Learning Discriminative Feature with CRF for Unsupervised Video Object Segmentation

Stochastic Bundle Adjustment for Efficient and Scalable 3D Reconstruction

GasMono: Geometry-Aided Self-Supervised Monocular Depth Estimation for Indoor Scenes

UniGraspTransformer: Simplified Policy Distillation for Scalable Dexterous Robotic Grasping

ROS-SAM: High-Quality Interactive Segmentation for Remote Sensing Moving Object

OxyGenerator: Reconstructing Global Ocean Deoxygenation Over a Century with Deep Learning

Learning Visual Proxy for Compositional Zero-Shot Learning

Where to Focus: Investigating Hierarchical Attention Relationship for Fine-Grained Visual Classification

papers (18)

BlendedMVS: A Large-Scale Dataset for Generalized Multi-View Stereo Networks

D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features

PointDSC: Robust Point Cloud Registration Using Deep Spatial Consistency

ASLFeat: Learning Local Features of Accurate Shape and Localization

ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer

Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware Multi-view Geometry Consistency

Learning To Match Features With Seeded Graph Matching Network

Goal-Oriented Gaze Estimation for Zero-Shot Learning

Joint Semantic Segmentation and Boundary Detection Using Iterative Pyramid Contexts

KFNet: Learning Temporal Camera Relocalization Using Kalman Filtering

Learning Discriminative Feature with CRF for Unsupervised Video Object Segmentation

Stochastic Bundle Adjustment for Efficient and Scalable 3D Reconstruction

GasMono: Geometry-Aided Self-Supervised Monocular Depth Estimation for Indoor Scenes

UniGraspTransformer: Simplified Policy Distillation for Scalable Dexterous Robotic Grasping

ROS-SAM: High-Quality Interactive Segmentation for Remote Sensing Moving Object

OxyGenerator: Reconstructing Global Ocean Deoxygenation Over a Century with Deep Learning

Learning Visual Proxy for Compositional Zero-Shot Learning

Where to Focus: Investigating Hierarchical Attention Relationship for Fine-Grained Visual Classification