Yinjie Lei

papers

769

total citations

papers (15)

Sparse-to-Dense Feature Matching: Intra and Inter Domain Cross-Modal Learning in Domain Adaptation for 3D Semantic Segmentation

ICCV 2021arXiv

citations

Unsupervised Image Denoising in Real-World Scenarios via Self-Collaboration Parallel Generative Adversarial Branches

ICCV 2023arXiv

citations

Deformation and Correspondence Aware Unsupervised Synthetic-to-Real Scene Flow Estimation for Point Clouds

CVPR 2022arXiv

citations

LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual Preferences

CVPR 2025arXiv

citations

ScanERU: Interactive 3D Visual Grounding Based on Embodied Reference Understanding

AAAI 2024arXiv

citations

Training-free Dense-Aligned Diffusion Guidance for Modular Conditional Image Synthesis

CVPR 2025arXiv

citations

Towards CLIP-driven Language-free 3D Visual Grounding via 2D-3D Relational Enhancement and Consistency

CVPR 2024

citations

Unsupervised Blind Image Deblurring Based on Self-Enhancement

CVPR 2024

citations

Context-Aware Alignment and Mutual Masking for 3D-Language Pre-Training

CVPR 2023

citations

Geometry and Uncertainty-Aware 3D Point Cloud Class-Incremental Semantic Segmentation

CVPR 2023

citations

Zero-Shot Point Cloud Segmentation by Semantic-Visual Aware Synthesis

ICCV 2023

citations

Yinjie Lei

papers (15)

ZegCLIP: Towards Adapting CLIP for Zero-Shot Semantic Segmentation

Semantic-Aware Domain Generalized Segmentation

End-to-End 3D Dense Captioning With Vote2Cap-DETR

Semi-Supervised Crowd Counting via Self-Training on Surrogate Tasks

Sparse-to-Dense Feature Matching: Intra and Inter Domain Cross-Modal Learning in Domain Adaptation for 3D Semantic Segmentation

Unsupervised Image Denoising in Real-World Scenarios via Self-Collaboration Parallel Generative Adversarial Branches

Deformation and Correspondence Aware Unsupervised Synthetic-to-Real Scene Flow Estimation for Point Clouds

LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual Preferences

ScanERU: Interactive 3D Visual Grounding Based on Embodied Reference Understanding

Training-free Dense-Aligned Diffusion Guidance for Modular Conditional Image Synthesis

Towards CLIP-driven Language-free 3D Visual Grounding via 2D-3D Relational Enhancement and Consistency

Unsupervised Blind Image Deblurring Based on Self-Enhancement

Context-Aware Alignment and Mutual Masking for 3D-Language Pre-Training

Geometry and Uncertainty-Aware 3D Point Cloud Class-Incremental Semantic Segmentation

Zero-Shot Point Cloud Segmentation by Semantic-Visual Aware Synthesis

papers (15)

ZegCLIP: Towards Adapting CLIP for Zero-Shot Semantic Segmentation

Semantic-Aware Domain Generalized Segmentation

End-to-End 3D Dense Captioning With Vote2Cap-DETR

Semi-Supervised Crowd Counting via Self-Training on Surrogate Tasks

Sparse-to-Dense Feature Matching: Intra and Inter Domain Cross-Modal Learning in Domain Adaptation for 3D Semantic Segmentation

Unsupervised Image Denoising in Real-World Scenarios via Self-Collaboration Parallel Generative Adversarial Branches

Deformation and Correspondence Aware Unsupervised Synthetic-to-Real Scene Flow Estimation for Point Clouds

LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual Preferences

ScanERU: Interactive 3D Visual Grounding Based on Embodied Reference Understanding

Training-free Dense-Aligned Diffusion Guidance for Modular Conditional Image Synthesis

Towards CLIP-driven Language-free 3D Visual Grounding via 2D-3D Relational Enhancement and Consistency

Unsupervised Blind Image Deblurring Based on Self-Enhancement

Context-Aware Alignment and Mutual Masking for 3D-Language Pre-Training

Geometry and Uncertainty-Aware 3D Point Cloud Class-Incremental Semantic Segmentation

Zero-Shot Point Cloud Segmentation by Semantic-Visual Aware Synthesis