Picture for Aljosa Osep

Aljosa Osep

Lidar Panoptic Segmentation in an Open World

Add code
Sep 22, 2024
Viaarxiv icon

Text2Pos: Text-to-Point-Cloud Cross-Modal Localization

Add code
Apr 05, 2022
Figure 1 for Text2Pos: Text-to-Point-Cloud Cross-Modal Localization
Figure 2 for Text2Pos: Text-to-Point-Cloud Cross-Modal Localization
Figure 3 for Text2Pos: Text-to-Point-Cloud Cross-Modal Localization
Figure 4 for Text2Pos: Text-to-Point-Cloud Cross-Modal Localization
Viaarxiv icon

Is Geometry Enough for Matching in Visual Localization?

Add code
Mar 24, 2022
Figure 1 for Is Geometry Enough for Matching in Visual Localization?
Figure 2 for Is Geometry Enough for Matching in Visual Localization?
Figure 3 for Is Geometry Enough for Matching in Visual Localization?
Figure 4 for Is Geometry Enough for Matching in Visual Localization?
Viaarxiv icon

MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?

Add code
Aug 21, 2021
Figure 1 for MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?
Figure 2 for MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?
Figure 3 for MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?
Figure 4 for MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?
Viaarxiv icon

STEP: Segmenting and Tracking Every Pixel

Add code
Feb 23, 2021
Figure 1 for STEP: Segmenting and Tracking Every Pixel
Figure 2 for STEP: Segmenting and Tracking Every Pixel
Figure 3 for STEP: Segmenting and Tracking Every Pixel
Figure 4 for STEP: Segmenting and Tracking Every Pixel
Viaarxiv icon

HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking

Add code
Sep 29, 2020
Figure 1 for HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking
Figure 2 for HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking
Figure 3 for HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking
Figure 4 for HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking
Viaarxiv icon

AlignNet-3D: Fast Point Cloud Registration of Partially Observed Objects

Add code
Oct 10, 2019
Figure 1 for AlignNet-3D: Fast Point Cloud Registration of Partially Observed Objects
Figure 2 for AlignNet-3D: Fast Point Cloud Registration of Partially Observed Objects
Figure 3 for AlignNet-3D: Fast Point Cloud Registration of Partially Observed Objects
Figure 4 for AlignNet-3D: Fast Point Cloud Registration of Partially Observed Objects
Viaarxiv icon

MOTS: Multi-Object Tracking and Segmentation

Add code
Apr 08, 2019
Figure 1 for MOTS: Multi-Object Tracking and Segmentation
Figure 2 for MOTS: Multi-Object Tracking and Segmentation
Figure 3 for MOTS: Multi-Object Tracking and Segmentation
Figure 4 for MOTS: Multi-Object Tracking and Segmentation
Viaarxiv icon

Large-Scale Object Mining for Object Discovery from Unlabeled Video

Add code
Feb 28, 2019
Figure 1 for Large-Scale Object Mining for Object Discovery from Unlabeled Video
Figure 2 for Large-Scale Object Mining for Object Discovery from Unlabeled Video
Figure 3 for Large-Scale Object Mining for Object Discovery from Unlabeled Video
Figure 4 for Large-Scale Object Mining for Object Discovery from Unlabeled Video
Viaarxiv icon

4D Generic Video Object Proposals

Add code
Jan 26, 2019
Figure 1 for 4D Generic Video Object Proposals
Figure 2 for 4D Generic Video Object Proposals
Figure 3 for 4D Generic Video Object Proposals
Figure 4 for 4D Generic Video Object Proposals
Viaarxiv icon