Picture for Liangji Fang

Liangji Fang

BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object Detection

Add code
Nov 17, 2022
Viaarxiv icon

AutoAlignV2: Deformable Feature Aggregation for Dynamic Multi-Modal 3D Object Detection

Add code
Jul 21, 2022
Figure 1 for AutoAlignV2: Deformable Feature Aggregation for Dynamic Multi-Modal 3D Object Detection
Figure 2 for AutoAlignV2: Deformable Feature Aggregation for Dynamic Multi-Modal 3D Object Detection
Figure 3 for AutoAlignV2: Deformable Feature Aggregation for Dynamic Multi-Modal 3D Object Detection
Figure 4 for AutoAlignV2: Deformable Feature Aggregation for Dynamic Multi-Modal 3D Object Detection
Viaarxiv icon

Towards Model Generalization for Monocular 3D Object Detection

Add code
May 28, 2022
Figure 1 for Towards Model Generalization for Monocular 3D Object Detection
Figure 2 for Towards Model Generalization for Monocular 3D Object Detection
Figure 3 for Towards Model Generalization for Monocular 3D Object Detection
Figure 4 for Towards Model Generalization for Monocular 3D Object Detection
Viaarxiv icon

Unsupervised Domain Adaptation for Monocular 3D Object Detection via Self-Training

Add code
Apr 27, 2022
Figure 1 for Unsupervised Domain Adaptation for Monocular 3D Object Detection via Self-Training
Figure 2 for Unsupervised Domain Adaptation for Monocular 3D Object Detection via Self-Training
Figure 3 for Unsupervised Domain Adaptation for Monocular 3D Object Detection via Self-Training
Figure 4 for Unsupervised Domain Adaptation for Monocular 3D Object Detection via Self-Training
Viaarxiv icon

Graph-DETR3D: Rethinking Overlapping Regions for Multi-View 3D Object Detection

Add code
Apr 26, 2022
Figure 1 for Graph-DETR3D: Rethinking Overlapping Regions for Multi-View 3D Object Detection
Figure 2 for Graph-DETR3D: Rethinking Overlapping Regions for Multi-View 3D Object Detection
Figure 3 for Graph-DETR3D: Rethinking Overlapping Regions for Multi-View 3D Object Detection
Figure 4 for Graph-DETR3D: Rethinking Overlapping Regions for Multi-View 3D Object Detection
Viaarxiv icon

AutoAlign: Pixel-Instance Feature Aggregation for Multi-Modal 3D Object Detection

Add code
Jan 17, 2022
Figure 1 for AutoAlign: Pixel-Instance Feature Aggregation for Multi-Modal 3D Object Detection
Figure 2 for AutoAlign: Pixel-Instance Feature Aggregation for Multi-Modal 3D Object Detection
Figure 3 for AutoAlign: Pixel-Instance Feature Aggregation for Multi-Modal 3D Object Detection
Figure 4 for AutoAlign: Pixel-Instance Feature Aggregation for Multi-Modal 3D Object Detection
Viaarxiv icon

SimIPU: Simple 2D Image and 3D Point Cloud Unsupervised Pre-Training for Spatial-Aware Visual Representations

Add code
Dec 09, 2021
Figure 1 for SimIPU: Simple 2D Image and 3D Point Cloud Unsupervised Pre-Training for Spatial-Aware Visual Representations
Figure 2 for SimIPU: Simple 2D Image and 3D Point Cloud Unsupervised Pre-Training for Spatial-Aware Visual Representations
Figure 3 for SimIPU: Simple 2D Image and 3D Point Cloud Unsupervised Pre-Training for Spatial-Aware Visual Representations
Figure 4 for SimIPU: Simple 2D Image and 3D Point Cloud Unsupervised Pre-Training for Spatial-Aware Visual Representations
Viaarxiv icon

Multimodal Motion Prediction with Stacked Transformers

Add code
Mar 24, 2021
Figure 1 for Multimodal Motion Prediction with Stacked Transformers
Figure 2 for Multimodal Motion Prediction with Stacked Transformers
Figure 3 for Multimodal Motion Prediction with Stacked Transformers
Figure 4 for Multimodal Motion Prediction with Stacked Transformers
Viaarxiv icon

TPNet: Trajectory Proposal Network for Motion Prediction

Add code
Apr 26, 2020
Figure 1 for TPNet: Trajectory Proposal Network for Motion Prediction
Figure 2 for TPNet: Trajectory Proposal Network for Motion Prediction
Figure 3 for TPNet: Trajectory Proposal Network for Motion Prediction
Figure 4 for TPNet: Trajectory Proposal Network for Motion Prediction
Viaarxiv icon

EdgeStereo: An Effective Multi-Task Learning Network for Stereo Matching and Edge Detection

Add code
Mar 05, 2019
Figure 1 for EdgeStereo: An Effective Multi-Task Learning Network for Stereo Matching and Edge Detection
Figure 2 for EdgeStereo: An Effective Multi-Task Learning Network for Stereo Matching and Edge Detection
Figure 3 for EdgeStereo: An Effective Multi-Task Learning Network for Stereo Matching and Edge Detection
Figure 4 for EdgeStereo: An Effective Multi-Task Learning Network for Stereo Matching and Edge Detection
Viaarxiv icon