Shaoshuai Shi

papers

4,495

total citations

papers (26)

PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection

CVPR 2020arXiv

2,131

citations

PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation

CVPR 2020arXiv

535

citations

Motion Transformer with Global Intention Localization and Local Movement Refinement

NEURIPS 2022arXiv

354

citations

Guided Point Contrastive Learning for Semi-Supervised Point Cloud Semantic Segmentation

ICCV 2021arXiv

135

citations

LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-Based 3D Detector

ICCV 2021arXiv

129

citations

Back-Tracing Representative Points for Voting-Based 3D Object Detection in Point Clouds

CVPR 2021arXiv

111

citations

MPPNet: Multi-Frame Feature Intertwining with Proxy Points for 3D Temporal Object Detection

ECCV 2022arXiv

citations

UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation

ICCV 2023arXiv

citations

CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Clouds

NEURIPS 2022arXiv

citations

RBGNet: Ray-Based Grouping for 3D Object Detection

CVPR 2022arXiv

citations

Towards Efficient 3D Object Detection with Knowledge Distillation

NEURIPS 2022arXiv

citations

ConQueR: Query Contrast Voxel-DETR for 3D Object Detection

CVPR 2023arXiv

citations

TrajectoryFormer: 3D Object Tracking Transformer with Predictive Trajectory Hypotheses

ICCV 2023arXiv

citations

SOLVE: Synergy of Language-Vision and End-to-End Networks for Autonomous Driving

CVPR 2025arXiv

citations

Self-Supervised Pre-Training With Masked Shape Prediction for 3D Scene Understanding

CVPR 2023arXiv

citations

M3Net: Multimodal Multi-task Learning for 3D Detection, Segmentation, and Occupancy Prediction in Autonomous Driving

AAAI 2025arXiv

citations

DriveX: Omni Scene Modeling for Learning Generalizable World Knowledge in Autonomous Driving

ICCV 2025arXiv

citations

Edit360: 2D Image Edits to 3D Assets from Any Angle

ICCV 2025arXiv

citations

Foresight in Motion: Reinforcing Trajectory Prediction with Reward Heuristics

ICCV 2025arXiv

citations

JiSAM: Alleviate Labeling Burden and Corner Case Problems in Autonomous Driving via Minimal Real-World Data

CVPR 2025arXiv

citations

CoIn: Contrastive Instance Feature Mining for Outdoor 3D Object Detection with Very Limited Annotations

ICCV 2023

citations

Open-Vocabulary 3D Semantic Segmentation with Foundation Models

CVPR 2024

citations

Enhancing Spatial Reasoning in Multimodal Large Language Models through Reasoning-based Segmentation

ICCV 2025arXiv

citations

Shaoshuai Shi

papers (26)

PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection

PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation

Motion Transformer with Global Intention Localization and Local Movement Refinement

ST3D: Self-Training for Unsupervised Domain Adaptation on 3D Object Detection

DSVT: Dynamic Sparse Voxel Transformer With Rotated Sets

Virtual Sparse Convolution for Multimodal 3D Object Detection

Guided Point Contrastive Learning for Semi-Supervised Point Cloud Semantic Segmentation

LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-Based 3D Detector

Back-Tracing Representative Points for Voting-Based 3D Object Detection in Point Clouds

MPPNet: Multi-Frame Feature Intertwining with Proxy Points for 3D Temporal Object Detection

UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation

CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Clouds

RBGNet: Ray-Based Grouping for 3D Object Detection

Towards Efficient 3D Object Detection with Knowledge Distillation

ConQueR: Query Contrast Voxel-DETR for 3D Object Detection

TrajectoryFormer: 3D Object Tracking Transformer with Predictive Trajectory Hypotheses

SOLVE: Synergy of Language-Vision and End-to-End Networks for Autonomous Driving

Self-Supervised Pre-Training With Masked Shape Prediction for 3D Scene Understanding

M3Net: Multimodal Multi-task Learning for 3D Detection, Segmentation, and Occupancy Prediction in Autonomous Driving

DriveX: Omni Scene Modeling for Learning Generalizable World Knowledge in Autonomous Driving

Edit360: 2D Image Edits to 3D Assets from Any Angle

Foresight in Motion: Reinforcing Trajectory Prediction with Reward Heuristics

JiSAM: Alleviate Labeling Burden and Corner Case Problems in Autonomous Driving via Minimal Real-World Data

CoIn: Contrastive Instance Feature Mining for Outdoor 3D Object Detection with Very Limited Annotations

Open-Vocabulary 3D Semantic Segmentation with Foundation Models

Enhancing Spatial Reasoning in Multimodal Large Language Models through Reasoning-based Segmentation

papers (26)

PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection

PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation

Motion Transformer with Global Intention Localization and Local Movement Refinement

ST3D: Self-Training for Unsupervised Domain Adaptation on 3D Object Detection

DSVT: Dynamic Sparse Voxel Transformer With Rotated Sets

Virtual Sparse Convolution for Multimodal 3D Object Detection

Guided Point Contrastive Learning for Semi-Supervised Point Cloud Semantic Segmentation

LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-Based 3D Detector

Back-Tracing Representative Points for Voting-Based 3D Object Detection in Point Clouds

MPPNet: Multi-Frame Feature Intertwining with Proxy Points for 3D Temporal Object Detection

UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation

CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Clouds

RBGNet: Ray-Based Grouping for 3D Object Detection

Towards Efficient 3D Object Detection with Knowledge Distillation

ConQueR: Query Contrast Voxel-DETR for 3D Object Detection

TrajectoryFormer: 3D Object Tracking Transformer with Predictive Trajectory Hypotheses

SOLVE: Synergy of Language-Vision and End-to-End Networks for Autonomous Driving

Self-Supervised Pre-Training With Masked Shape Prediction for 3D Scene Understanding

M3Net: Multimodal Multi-task Learning for 3D Detection, Segmentation, and Occupancy Prediction in Autonomous Driving

DriveX: Omni Scene Modeling for Learning Generalizable World Knowledge in Autonomous Driving

Edit360: 2D Image Edits to 3D Assets from Any Angle

Foresight in Motion: Reinforcing Trajectory Prediction with Reward Heuristics

JiSAM: Alleviate Labeling Burden and Corner Case Problems in Autonomous Driving via Minimal Real-World Data

CoIn: Contrastive Instance Feature Mining for Outdoor 3D Object Detection with Very Limited Annotations

Open-Vocabulary 3D Semantic Segmentation with Foundation Models

Enhancing Spatial Reasoning in Multimodal Large Language Models through Reasoning-based Segmentation