Yikang Li

papers

1,193

total citations

papers (17)

LoGoNet: Towards Accurate 3D Object Detection With Local-to-Global Cross-Modal Fusion

CVPR 2023arXiv

150

citations

SCPNet: Semantic Scene Completion on Point Cloud

CVPR 2023arXiv

110

citations

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

ICCV 2023arXiv

citations

Homogeneous Multi-modal Feature Fusion and Interaction for 3D Object Detection

ECCV 2022arXiv

citations

Uni3D: A Unified Baseline for Multi-Dataset 3D Object Detection

CVPR 2023arXiv

citations

DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point Clouds

ICCV 2023arXiv

citations

Bi3D: Bi-Domain Active Learning for Cross-Domain 3D Object Detection

CVPR 2023arXiv

citations

Catch Missing Details: Image Reconstruction With Frequency Augmented Variational Autoencoder

CVPR 2023arXiv

citations

Optimizing the Placement of Roadside LiDARs for Autonomous Driving

ICCV 2023arXiv

citations

RhyRNN: Rhythmic RNN for Recognizing Events in Long and Complex Videos

ECCV 2020

citations

L-Tracing: Fast Light Visibility Estimation on Neural Surfaces by Sphere Tracing

ECCV 2022

citations

b-DARTS: Beta-Decay Regularization for Differentiable Architecture Search

CVPR 2022

citations

Affine Equivariant Networks Based on Differential Invariants

CVPR 2024

citations

Explicit Discovery of Nonlinear Symmetries from Dynamic Data

ICML 2025arXiv

citations

Yikang Li

papers (17)

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

LoGoNet: Towards Accurate 3D Object Detection With Local-to-Global Cross-Modal Fusion

SCPNet: Semantic Scene Completion on Point Cloud

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

Homogeneous Multi-modal Feature Fusion and Interaction for 3D Object Detection

Uni3D: A Unified Baseline for Multi-Dataset 3D Object Detection

DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point Clouds

Bi3D: Bi-Domain Active Learning for Cross-Domain 3D Object Detection

Catch Missing Details: Image Reconstruction With Frequency Augmented Variational Autoencoder

Optimizing the Placement of Roadside LiDARs for Autonomous Driving

RhyRNN: Rhythmic RNN for Recognizing Events in Long and Complex Videos

L-Tracing: Fast Light Visibility Estimation on Neural Surfaces by Sphere Tracing

b-DARTS: Beta-Decay Regularization for Differentiable Architecture Search

Affine Equivariant Networks Based on Differential Invariants

Explicit Discovery of Nonlinear Symmetries from Dynamic Data

papers (17)

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

LoGoNet: Towards Accurate 3D Object Detection With Local-to-Global Cross-Modal Fusion

SCPNet: Semantic Scene Completion on Point Cloud

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

Homogeneous Multi-modal Feature Fusion and Interaction for 3D Object Detection

Uni3D: A Unified Baseline for Multi-Dataset 3D Object Detection

DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point Clouds

Bi3D: Bi-Domain Active Learning for Cross-Domain 3D Object Detection

Catch Missing Details: Image Reconstruction With Frequency Augmented Variational Autoencoder

Optimizing the Placement of Roadside LiDARs for Autonomous Driving

RhyRNN: Rhythmic RNN for Recognizing Events in Long and Complex Videos

L-Tracing: Fast Light Visibility Estimation on Neural Surfaces by Sphere Tracing

b-DARTS: Beta-Decay Regularization for Differentiable Architecture Search

Affine Equivariant Networks Based on Differential Invariants

Explicit Discovery of Nonlinear Symmetries from Dynamic Data