Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Bastian Leibe

Bastian Leibe

Person-MinkUNet: 3D Person Detection with LiDAR Point Cloud


Jul 03, 2021
Dan Jia, Bastian Leibe

* accepted as an extended abstract in JRDB-ACT Workshop at CVPR21 
  Access Paper or Ask Questions

Domain and Modality Gaps for LiDAR-based Person Detection on Mobile Robots


Jun 21, 2021
Dan Jia, Alexander Hermans, Bastian Leibe

Figure 1 for Domain and Modality Gaps for LiDAR-based Person Detection on Mobile Robots
Figure 2 for Domain and Modality Gaps for LiDAR-based Person Detection on Mobile Robots
Figure 3 for Domain and Modality Gaps for LiDAR-based Person Detection on Mobile Robots
Figure 4 for Domain and Modality Gaps for LiDAR-based Person Detection on Mobile Robots

  Access Paper or Ask Questions

Opening up Open-World Tracking


Apr 22, 2021
Yang Liu, Idil Esen Zulfikar, Jonathon Luiten, Achal Dave, Aljoša Ošep, Deva Ramanan, Bastian Leibe, Laura Leal-Taixé

Figure 1 for Opening up Open-World Tracking
Figure 2 for Opening up Open-World Tracking
Figure 3 for Opening up Open-World Tracking
Figure 4 for Opening up Open-World Tracking

  Access Paper or Ask Questions

STEP: Segmenting and Tracking Every Pixel


Feb 23, 2021
Mark Weber, Jun Xie, Maxwell Collins, Yukun Zhu, Paul Voigtlaender, Hartwig Adam, Bradley Green, Andreas Geiger, Bastian Leibe, Daniel Cremers, Aljosa Osep, Laura Leal-Taixe, Liang-Chieh Chen

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
* Datasets, metric, and baselines will be made publicly available soon 
  Access Paper or Ask Questions

From Points to Multi-Object 3D Reconstruction


Dec 21, 2020
Francis Engelmann, Konstantinos Rematas, Bastian Leibe, Vittorio Ferrari

Figure 1 for From Points to Multi-Object 3D Reconstruction
Figure 2 for From Points to Multi-Object 3D Reconstruction
Figure 3 for From Points to Multi-Object 3D Reconstruction
Figure 4 for From Points to Multi-Object 3D Reconstruction

  Access Paper or Ask Questions

Self-Supervised Person Detection in 2D Range Data using a Calibrated Camera


Dec 16, 2020
Dan Jia, Mats Steinweg, Alexander Hermans, Bastian Leibe

Figure 1 for Self-Supervised Person Detection in 2D Range Data using a Calibrated Camera
Figure 2 for Self-Supervised Person Detection in 2D Range Data using a Calibrated Camera
Figure 3 for Self-Supervised Person Detection in 2D Range Data using a Calibrated Camera
Figure 4 for Self-Supervised Person Detection in 2D Range Data using a Calibrated Camera

  Access Paper or Ask Questions

Reducing the Annotation Effort for Video Object Segmentation Datasets


Nov 02, 2020
Paul Voigtlaender, Lishu Luo, Chun Yuan, Yong Jiang, Bastian Leibe

Figure 1 for Reducing the Annotation Effort for Video Object Segmentation Datasets
Figure 2 for Reducing the Annotation Effort for Video Object Segmentation Datasets
Figure 3 for Reducing the Annotation Effort for Video Object Segmentation Datasets
Figure 4 for Reducing the Annotation Effort for Video Object Segmentation Datasets
* Accepted at WACV 2021 
  Access Paper or Ask Questions

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


Sep 29, 2020
Jonathon Luiten, Aljosa Osep, Patrick Dendorfer, Philip Torr, Andreas Geiger, Laura Leal-Taixe, Bastian Leibe

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
* Pre-print. Accepted for Publication in the International Journal of Computer Vision, 19 August 2020. Code is available at https://github.com/JonathonLuiten/HOTA-metrics 
  Access Paper or Ask Questions

Making a Case for 3D Convolutions for Object Segmentation in Videos


Aug 26, 2020
Sabarinath Mahadevan, Ali Athar, Aljoša Ošep, Sebastian Hennen, Laura Leal-Taixé, Bastian Leibe

Figure 1 for Making a Case for 3D Convolutions for Object Segmentation in Videos
Figure 2 for Making a Case for 3D Convolutions for Object Segmentation in Videos
Figure 3 for Making a Case for 3D Convolutions for Object Segmentation in Videos
Figure 4 for Making a Case for 3D Convolutions for Object Segmentation in Videos
* BMVC '20 
  Access Paper or Ask Questions

MeTRAbs: Metric-Scale Truncation-Robust Heatmaps for Absolute 3D Human Pose Estimation


Jul 12, 2020
István Sárándi, Timm Linder, Kai O. Arras, Bastian Leibe

Figure 1 for MeTRAbs: Metric-Scale Truncation-Robust Heatmaps for Absolute 3D Human Pose Estimation
Figure 2 for MeTRAbs: Metric-Scale Truncation-Robust Heatmaps for Absolute 3D Human Pose Estimation
Figure 3 for MeTRAbs: Metric-Scale Truncation-Robust Heatmaps for Absolute 3D Human Pose Estimation
Figure 4 for MeTRAbs: Metric-Scale Truncation-Robust Heatmaps for Absolute 3D Human Pose Estimation
* Project page: https://vision.rwth-aachen.de/metrabs. arXiv admin note: substantial text overlap with arXiv:2003.02953 
  Access Paper or Ask Questions

Reposing Humans by Warping 3D Features


Jun 08, 2020
Markus Knoche, István Sárándi, Bastian Leibe

Figure 1 for Reposing Humans by Warping 3D Features
Figure 2 for Reposing Humans by Warping 3D Features
Figure 3 for Reposing Humans by Warping 3D Features
Figure 4 for Reposing Humans by Warping 3D Features
* Accepted at CVPR 2020 Workshop on Human-Centric Image/Video Synthesis 
  Access Paper or Ask Questions

Self-supervised Keypoint Correspondences for Multi-Person Pose Estimation and Tracking in Videos


Jun 02, 2020
Umer Rafi, Andreas Doering, Bastian Leibe, Juergen Gall

Figure 1 for Self-supervised Keypoint Correspondences for Multi-Person Pose Estimation and Tracking in Videos
Figure 2 for Self-supervised Keypoint Correspondences for Multi-Person Pose Estimation and Tracking in Videos
Figure 3 for Self-supervised Keypoint Correspondences for Multi-Person Pose Estimation and Tracking in Videos
Figure 4 for Self-supervised Keypoint Correspondences for Multi-Person Pose Estimation and Tracking in Videos
* Submitted to ECCV 2020 
  Access Paper or Ask Questions

SAMP: Shape and Motion Priors for 4D Vehicle Reconstruction


May 02, 2020
Francis Engelmann, Jörg Stückler, Bastian Leibe

Figure 1 for SAMP: Shape and Motion Priors for 4D Vehicle Reconstruction
Figure 2 for SAMP: Shape and Motion Priors for 4D Vehicle Reconstruction
Figure 3 for SAMP: Shape and Motion Priors for 4D Vehicle Reconstruction
Figure 4 for SAMP: Shape and Motion Priors for 4D Vehicle Reconstruction
* IEEE Winter Conference on Applications of Computer Vision (WACV), 2017 
  Access Paper or Ask Questions

DR-SPAAM: A Spatial-Attention and Auto-regressive Model for Person Detection in 2D Range Data


Apr 29, 2020
Dan Jia, Alexander Hermans, Bastian Leibe

Figure 1 for DR-SPAAM: A Spatial-Attention and Auto-regressive Model for Person Detection in 2D Range Data
Figure 2 for DR-SPAAM: A Spatial-Attention and Auto-regressive Model for Person Detection in 2D Range Data
Figure 3 for DR-SPAAM: A Spatial-Attention and Auto-regressive Model for Person Detection in 2D Range Data
Figure 4 for DR-SPAAM: A Spatial-Attention and Auto-regressive Model for Person Detection in 2D Range Data

  Access Paper or Ask Questions

STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos


Apr 10, 2020
Ali Athar, Sabarinath Mahadevan, Aljoša Ošep, Laura Leal-Taixé, Bastian Leibe

Figure 1 for STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos
Figure 2 for STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos
Figure 3 for STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos
Figure 4 for STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos
* 28 pages, 6 figures 
  Access Paper or Ask Questions

DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes


Apr 02, 2020
Jonas Schult, Francis Engelmann, Theodora Kontogianni, Bastian Leibe

Figure 1 for DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes
Figure 2 for DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes
Figure 3 for DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes
Figure 4 for DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes
* CVPR 2020 camera-ready version 
  Access Paper or Ask Questions

3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation


Mar 30, 2020
Francis Engelmann, Martin Bokeloh, Alireza Fathi, Bastian Leibe, Matthias Nießner

Figure 1 for 3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation
Figure 2 for 3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation
Figure 3 for 3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation
Figure 4 for 3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation
* CVPR2020, Video: https://youtu.be/ifL8yTbRFDk Project Page: https://www.vision.rwth-aachen.de/3d_instance_segmentation/ 
  Access Paper or Ask Questions

Metric-Scale Truncation-Robust Heatmaps for 3D Human Pose Estimation


Mar 05, 2020
István Sárándi, Timm Linder, Kai O. Arras, Bastian Leibe

Figure 1 for Metric-Scale Truncation-Robust Heatmaps for 3D Human Pose Estimation
Figure 2 for Metric-Scale Truncation-Robust Heatmaps for 3D Human Pose Estimation
Figure 3 for Metric-Scale Truncation-Robust Heatmaps for 3D Human Pose Estimation
Figure 4 for Metric-Scale Truncation-Robust Heatmaps for 3D Human Pose Estimation
* Accepted for publication at the 2020 IEEE Conference on Automatic Face and Gesture Recognition (FG) 
  Access Paper or Ask Questions

UnOVOST: Unsupervised Offline Video Object Segmentation and Tracking


Jan 15, 2020
Jonathon Luiten, Idil Esen Zulfikar, Bastian Leibe

Figure 1 for UnOVOST: Unsupervised Offline Video Object Segmentation and Tracking
Figure 2 for UnOVOST: Unsupervised Offline Video Object Segmentation and Tracking
Figure 3 for UnOVOST: Unsupervised Offline Video Object Segmentation and Tracking
Figure 4 for UnOVOST: Unsupervised Offline Video Object Segmentation and Tracking
* Accepted for publication at WACV 2020 
  Access Paper or Ask Questions

Siam R-CNN: Visual Tracking by Re-Detection


Nov 28, 2019
Paul Voigtlaender, Jonathon Luiten, Philip H. S. Torr, Bastian Leibe

Figure 1 for Siam R-CNN: Visual Tracking by Re-Detection
Figure 2 for Siam R-CNN: Visual Tracking by Re-Detection
Figure 3 for Siam R-CNN: Visual Tracking by Re-Detection
Figure 4 for Siam R-CNN: Visual Tracking by Re-Detection

  Access Paper or Ask Questions

Single-Shot Panoptic Segmentation


Nov 02, 2019
Mark Weber, Jonathon Luiten, Bastian Leibe

Figure 1 for Single-Shot Panoptic Segmentation
Figure 2 for Single-Shot Panoptic Segmentation
Figure 3 for Single-Shot Panoptic Segmentation
Figure 4 for Single-Shot Panoptic Segmentation

  Access Paper or Ask Questions

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


Oct 10, 2019
Johannes Groß, Aljosa Osep, Bastian Leibe

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
* Presented at 3DV'19 
  Access Paper or Ask Questions

Track to Reconstruct and Reconstruct to Track


Sep 30, 2019
Jonathon Luiten, Tobias Fischer, Bastian Leibe

Figure 1 for Track to Reconstruct and Reconstruct to Track
Figure 2 for Track to Reconstruct and Reconstruct to Track
Figure 3 for Track to Reconstruct and Reconstruct to Track
Figure 4 for Track to Reconstruct and Reconstruct to Track

  Access Paper or Ask Questions

Dilated Point Convolutions: On the Receptive Field of Point Convolutions


Jul 28, 2019
Francis Engelmann, Theodora Kontogianni, Bastian Leibe

Figure 1 for Dilated Point Convolutions: On the Receptive Field of Point Convolutions
Figure 2 for Dilated Point Convolutions: On the Receptive Field of Point Convolutions
Figure 3 for Dilated Point Convolutions: On the Receptive Field of Point Convolutions
Figure 4 for Dilated Point Convolutions: On the Receptive Field of Point Convolutions

  Access Paper or Ask Questions

Visual Person Understanding through Multi-Task and Multi-Dataset Learning


Jun 07, 2019
Kilian Pfeiffer, Alexander Hermans, István Sárándi, Mark Weber, Bastian Leibe

Figure 1 for Visual Person Understanding through Multi-Task and Multi-Dataset Learning
Figure 2 for Visual Person Understanding through Multi-Task and Multi-Dataset Learning
Figure 3 for Visual Person Understanding through Multi-Task and Multi-Dataset Learning
Figure 4 for Visual Person Understanding through Multi-Task and Multi-Dataset Learning

  Access Paper or Ask Questions

3D-BEVIS: Birds-Eye-View Instance Segmentation


May 17, 2019
Cathrin Elich, Francis Engelmann, Jonas Schult, Theodora Kontogianni, Bastian Leibe

Figure 1 for 3D-BEVIS: Birds-Eye-View Instance Segmentation
Figure 2 for 3D-BEVIS: Birds-Eye-View Instance Segmentation
Figure 3 for 3D-BEVIS: Birds-Eye-View Instance Segmentation
Figure 4 for 3D-BEVIS: Birds-Eye-View Instance Segmentation
* Technical Report 
  Access Paper or Ask Questions

BoLTVOS: Box-Level Tracking for Video Object Segmentation


Apr 09, 2019
Paul Voigtlaender, Jonathon Luiten, Bastian Leibe

Figure 1 for BoLTVOS: Box-Level Tracking for Video Object Segmentation
Figure 2 for BoLTVOS: Box-Level Tracking for Video Object Segmentation
Figure 3 for BoLTVOS: Box-Level Tracking for Video Object Segmentation
Figure 4 for BoLTVOS: Box-Level Tracking for Video Object Segmentation

  Access Paper or Ask Questions