Xinge Zhu

papers

2,731

total citations

papers (24)

TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection With Transformers

CVPR 2022arXiv

827

citations

UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebase

ICCV 2023arXiv

citations

AdaStereo: A Simple and Efficient Approach for Adaptive Stereo Matching

CVPR 2021arXiv

citations

Tensor Low-Rank Reconstruction for Semantic Segmentation

ECCV 2020arXiv

citations

STCrowd: A Multimodal Dataset for Pedestrian Perception in Crowded Scenes

CVPR 2022arXiv

citations

Human-centric Scene Understanding for 3D Large-scale Scenarios

ICCV 2023arXiv

citations

See More and Know More: Zero-shot Point Cloud Segmentation via Multi-modal Visual Data

ICCV 2023arXiv

citations

PARTNER: Level up the Polar Representation for LiDAR 3D Object Detection

ICCV 2023arXiv

citations

Can LVLMs Obtain a Driver’s License? A Benchmark Towards Reliable AGI for Autonomous Driving

AAAI 2025arXiv

citations

TASeg: Temporal Aggregation Network for LiDAR Semantic Segmentation

CVPR 2024arXiv

citations

AutoTrajectory: Label-free Trajectory Extraction and Prediction from Videos using Dynamic Points

ECCV 2020arXiv

citations

ReAL-AD: Towards Human-Like Reasoning in End-to-End Autonomous Driving

ICCV 2025arXiv

citations

A Unified Framework for Human-centric Point Cloud Video Understanding

CVPR 2024arXiv

citations

HUNTER: Unsupervised Human-centric 3D Detection via Transferring Knowledge from Synthetic Instances to Real Scenes

CVPR 2024arXiv

citations

EvolvingGrasp: Evolutionary Grasp Generation via Efficient Preference Alignment

ICCV 2025arXiv

citations

FreeCap: Hybrid Calibration-Free Motion Capture in Open Environments

AAAI 2025arXiv

citations

FreqPolicy: Frequency Autoregressive Visuomotor Policy with Continuous Tokens

NEURIPS 2025arXiv

citations

Efficient Point Cloud Analysis Using Hilbert Curve

ECCV 2022

citations

Xinge Zhu

papers (24)

TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection With Transformers

Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation

CLIP2Scene: Towards Label-Efficient 3D Scene Understanding by CLIP

Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation

Rethinking Range View Representation for LiDAR Segmentation

LiDAR-Based Panoptic Segmentation via Dynamic Shifting Network

SCPNet: Semantic Scene Completion on Point Cloud

UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebase

AdaStereo: A Simple and Efficient Approach for Adaptive Stereo Matching

Tensor Low-Rank Reconstruction for Semantic Segmentation

STCrowd: A Multimodal Dataset for Pedestrian Perception in Crowded Scenes

Human-centric Scene Understanding for 3D Large-scale Scenarios

See More and Know More: Zero-shot Point Cloud Segmentation via Multi-modal Visual Data

PARTNER: Level up the Polar Representation for LiDAR 3D Object Detection

Can LVLMs Obtain a Driver’s License? A Benchmark Towards Reliable AGI for Autonomous Driving

TASeg: Temporal Aggregation Network for LiDAR Semantic Segmentation

AutoTrajectory: Label-free Trajectory Extraction and Prediction from Videos using Dynamic Points

ReAL-AD: Towards Human-Like Reasoning in End-to-End Autonomous Driving

A Unified Framework for Human-centric Point Cloud Video Understanding

HUNTER: Unsupervised Human-centric 3D Detection via Transferring Knowledge from Synthetic Instances to Real Scenes

EvolvingGrasp: Evolutionary Grasp Generation via Efficient Preference Alignment

FreeCap: Hybrid Calibration-Free Motion Capture in Open Environments

FreqPolicy: Frequency Autoregressive Visuomotor Policy with Continuous Tokens

Efficient Point Cloud Analysis Using Hilbert Curve

papers (24)

TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection With Transformers

Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation

CLIP2Scene: Towards Label-Efficient 3D Scene Understanding by CLIP

Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation

Rethinking Range View Representation for LiDAR Segmentation

LiDAR-Based Panoptic Segmentation via Dynamic Shifting Network

SCPNet: Semantic Scene Completion on Point Cloud

UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebase

AdaStereo: A Simple and Efficient Approach for Adaptive Stereo Matching

Tensor Low-Rank Reconstruction for Semantic Segmentation

STCrowd: A Multimodal Dataset for Pedestrian Perception in Crowded Scenes

Human-centric Scene Understanding for 3D Large-scale Scenarios

See More and Know More: Zero-shot Point Cloud Segmentation via Multi-modal Visual Data

PARTNER: Level up the Polar Representation for LiDAR 3D Object Detection

Can LVLMs Obtain a Driver’s License? A Benchmark Towards Reliable AGI for Autonomous Driving

TASeg: Temporal Aggregation Network for LiDAR Semantic Segmentation

AutoTrajectory: Label-free Trajectory Extraction and Prediction from Videos using Dynamic Points

ReAL-AD: Towards Human-Like Reasoning in End-to-End Autonomous Driving

A Unified Framework for Human-centric Point Cloud Video Understanding

HUNTER: Unsupervised Human-centric 3D Detection via Transferring Knowledge from Synthetic Instances to Real Scenes

EvolvingGrasp: Evolutionary Grasp Generation via Efficient Preference Alignment

FreeCap: Hybrid Calibration-Free Motion Capture in Open Environments

FreqPolicy: Frequency Autoregressive Visuomotor Policy with Continuous Tokens

Efficient Point Cloud Analysis Using Hilbert Curve