Lingdong Kong

papers

1,283

total citations

papers (23)

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

ICCV 2023arXiv

citations

Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data and Metric Perspectives

ICCV 2025arXiv

citations

Towards Label-free Scene Understanding by Vision Foundation Models

NEURIPS 2023arXiv

citations

RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions

NEURIPS 2023arXiv

citations

SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding

CVPR 2025arXiv

citations

OpenESS: Event-based Semantic Scene Understanding with Open Vocabularies

CVPR 2024arXiv

citations

Multi-Space Alignments Towards Universal LiDAR Segmentation

CVPR 2024arXiv

citations

Unsupervised Video Domain Adaptation for Action Recognition: A Disentanglement Perspective

NEURIPS 2023arXiv

citations

Learning to Adapt SAM for Segmenting Cross-domain Point Clouds

ECCV 2024arXiv

citations

LiMoE: Mixture of LiDAR Representation Learners from Automotive Scenes

CVPR 2025arXiv

citations

GEAL: Generalizable 3D Affordance Learning with Cross-Modal Consistency

CVPR 2025arXiv

citations

Perspective-Invariant 3D Object Detection

ICCV 2025arXiv

citations

EventFly: Event Camera Perception from Ground to the Sky

CVPR 2025arXiv

citations

Beyond One Shot, Beyond One Perspective: Cross-View and Long-Horizon Distillation for Better LiDAR Representations

ICCV 2025arXiv

citations

Spiral: Semantic-Aware Progressive LiDAR Scene Generation and Understanding

NEURIPS 2025arXiv

citations

PointLoRA: Low-Rank Adaptation with Token Selection for Point Cloud Learning

CVPR 2025arXiv

citations

Monocular Semantic Scene Completion via Masked Recurrent Networks

ICCV 2025arXiv

citations

VideoLucy: Deep Memory Backtracking for Long Video Understanding

NEURIPS 2025arXiv

citations

Lingdong Kong

papers (23)

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

Rethinking Range View Representation for LiDAR Segmentation

Segment Any Point Cloud Sequences by Distilling Vision Foundation Models

Robo3D: Towards Robust and Reliable 3D Perception against Corruptions

LaserMix for Semi-Supervised LiDAR Semantic Segmentation

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

Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data and Metric Perspectives

Towards Label-free Scene Understanding by Vision Foundation Models

RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions

SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding

OpenESS: Event-based Semantic Scene Understanding with Open Vocabularies

Multi-Space Alignments Towards Universal LiDAR Segmentation

Unsupervised Video Domain Adaptation for Action Recognition: A Disentanglement Perspective

Learning to Adapt SAM for Segmenting Cross-domain Point Clouds

LiMoE: Mixture of LiDAR Representation Learners from Automotive Scenes

GEAL: Generalizable 3D Affordance Learning with Cross-Modal Consistency

Perspective-Invariant 3D Object Detection

EventFly: Event Camera Perception from Ground to the Sky

Beyond One Shot, Beyond One Perspective: Cross-View and Long-Horizon Distillation for Better LiDAR Representations

Spiral: Semantic-Aware Progressive LiDAR Scene Generation and Understanding

PointLoRA: Low-Rank Adaptation with Token Selection for Point Cloud Learning

Monocular Semantic Scene Completion via Masked Recurrent Networks

VideoLucy: Deep Memory Backtracking for Long Video Understanding

papers (23)

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

Rethinking Range View Representation for LiDAR Segmentation

Segment Any Point Cloud Sequences by Distilling Vision Foundation Models

Robo3D: Towards Robust and Reliable 3D Perception against Corruptions

LaserMix for Semi-Supervised LiDAR Semantic Segmentation

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

Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data and Metric Perspectives

Towards Label-free Scene Understanding by Vision Foundation Models

RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions

SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding

OpenESS: Event-based Semantic Scene Understanding with Open Vocabularies

Multi-Space Alignments Towards Universal LiDAR Segmentation

Unsupervised Video Domain Adaptation for Action Recognition: A Disentanglement Perspective

Learning to Adapt SAM for Segmenting Cross-domain Point Clouds

LiMoE: Mixture of LiDAR Representation Learners from Automotive Scenes

GEAL: Generalizable 3D Affordance Learning with Cross-Modal Consistency

Perspective-Invariant 3D Object Detection

EventFly: Event Camera Perception from Ground to the Sky

Beyond One Shot, Beyond One Perspective: Cross-View and Long-Horizon Distillation for Better LiDAR Representations

Spiral: Semantic-Aware Progressive LiDAR Scene Generation and Understanding

PointLoRA: Low-Rank Adaptation with Token Selection for Point Cloud Learning

Monocular Semantic Scene Completion via Masked Recurrent Networks

VideoLucy: Deep Memory Backtracking for Long Video Understanding