Lu Fang

papers

773

total citations

papers (19)

OccuSeg: Occupancy-Aware 3D Instance Segmentation

CVPR 2020arXiv

290

citations

EventCap: Monocular 3D Capture of High-Speed Human Motions Using an Event Camera

CVPR 2020arXiv

119

citations

PANDA: A Gigapixel-Level Human-Centric Video Dataset

CVPR 2020arXiv

citations

Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detection

CVPR 2021arXiv

citations

OmniSeg3D: Omniversal 3D Segmentation via Hierarchical Contrastive Learning

CVPR 2024arXiv

citations

LocalTrans: A Multiscale Local Transformer Network for Cross-Resolution Homography Estimation

ICCV 2021arXiv

citations

SVQNet: Sparse Voxel-Adjacent Query Network for 4D Spatio-Temporal LiDAR Semantic Segmentation

ICCV 2023arXiv

citations

Crowd3D: Towards Hundreds of People Reconstruction From a Single Image

CVPR 2023arXiv

citations

When Visual Grounding Meets Gigapixel-level Large-scale Scenes: Benchmark and Approach

CVPR 2024

citations

SPECAT: SPatial-spEctral Cumulative-Attention Transformer for High-Resolution Hyperspectral Image Reconstruction

CVPR 2024

citations

RobustFusion: Human Volumetric Capture with Data-driven Visual Cues using a RGBD Camera

ECCV 2020

citations

INS-Conv: Incremental Sparse Convolution for Online 3D Segmentation

CVPR 2022

citations

DartBlur: Privacy Preservation With Detection Artifact Suppression

CVPR 2023

citations

GigaTraj: Predicting Long-term Trajectories of Hundreds of Pedestrians in Gigapixel Complex Scenes

CVPR 2024

citations

A2-FPN: Attention Aggregation Based Feature Pyramid Network for Instance Segmentation

CVPR 2021

citations

Lu Fang

papers (19)

OccuSeg: Occupancy-Aware 3D Instance Segmentation

EventCap: Monocular 3D Capture of High-Speed Human Motions Using an Event Camera

PANDA: A Gigapixel-Level Human-Centric Video Dataset

Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detection

OmniSeg3D: Omniversal 3D Segmentation via Hierarchical Contrastive Learning

LocalTrans: A Multiscale Local Transformer Network for Cross-Resolution Homography Estimation

SVQNet: Sparse Voxel-Adjacent Query Network for 4D Spatio-Temporal LiDAR Semantic Segmentation

Crowd3D: Towards Hundreds of People Reconstruction From a Single Image

When Visual Grounding Meets Gigapixel-level Large-scale Scenes: Benchmark and Approach

GigaHumanDet: Exploring Full-Body Detection on Gigapixel-Level Images

PARF: Primitive-Aware Radiance Fusion for Indoor Scene Novel View Synthesis

XScale-NVS: Cross-Scale Novel View Synthesis with Hash Featurized Manifold

RealGraph: A Multiview Dataset for 4D Real-world Context Graph Generation

SPECAT: SPatial-spEctral Cumulative-Attention Transformer for High-Resolution Hyperspectral Image Reconstruction

RobustFusion: Human Volumetric Capture with Data-driven Visual Cues using a RGBD Camera

INS-Conv: Incremental Sparse Convolution for Online 3D Segmentation

DartBlur: Privacy Preservation With Detection Artifact Suppression

GigaTraj: Predicting Long-term Trajectories of Hundreds of Pedestrians in Gigapixel Complex Scenes

A2-FPN: Attention Aggregation Based Feature Pyramid Network for Instance Segmentation

papers (19)

OccuSeg: Occupancy-Aware 3D Instance Segmentation

EventCap: Monocular 3D Capture of High-Speed Human Motions Using an Event Camera

PANDA: A Gigapixel-Level Human-Centric Video Dataset

Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detection

OmniSeg3D: Omniversal 3D Segmentation via Hierarchical Contrastive Learning

LocalTrans: A Multiscale Local Transformer Network for Cross-Resolution Homography Estimation

SVQNet: Sparse Voxel-Adjacent Query Network for 4D Spatio-Temporal LiDAR Semantic Segmentation

Crowd3D: Towards Hundreds of People Reconstruction From a Single Image

When Visual Grounding Meets Gigapixel-level Large-scale Scenes: Benchmark and Approach

GigaHumanDet: Exploring Full-Body Detection on Gigapixel-Level Images

PARF: Primitive-Aware Radiance Fusion for Indoor Scene Novel View Synthesis

XScale-NVS: Cross-Scale Novel View Synthesis with Hash Featurized Manifold

RealGraph: A Multiview Dataset for 4D Real-world Context Graph Generation

SPECAT: SPatial-spEctral Cumulative-Attention Transformer for High-Resolution Hyperspectral Image Reconstruction

RobustFusion: Human Volumetric Capture with Data-driven Visual Cues using a RGBD Camera

INS-Conv: Incremental Sparse Convolution for Online 3D Segmentation

DartBlur: Privacy Preservation With Detection Artifact Suppression

GigaTraj: Predicting Long-term Trajectories of Hundreds of Pedestrians in Gigapixel Complex Scenes

A2-FPN: Attention Aggregation Based Feature Pyramid Network for Instance Segmentation