July 8th, 2021 
Daniela Lopez de Luise This is an invitation to attend the 3D-DLAD-v3 (3rd 3D Deep Learning for Autonomous Driving) workshop organized as a part of the flagship automotive conference Intelligent Vehicles 2021 https://2021.ieee-iv.org/.
The workshop will be held on 11th July virtually. The workshop hosts an exceptional list of invited speakers & interesting paper presentations.
The schedule of the workshop can be found here : https://sites.google.com/view/3d-dlad-v3-iv2021/schedule
The workshop shall be streamed live on zoom, though this requires a free but necessary registration as mentioned here under free registration: https://2021.ieee-iv.org/registration/
Finalized Schedule : Time zone CET
Finalized Schedule : Time zone CET
Length : Full day workshop
09:00-09:10 : Introduction
09:10-09:40: On Monocular Depth Estimation: (1) MonoDEVS ; (2) Multi-modal Co-training, Dr. Antonio M. López
09:40-10:10: Point-based recognition, Prof. Philipp Krähenbühl
10:10-10:40: Lidar Segmentation at Motional, Venice Liong
10:40-11:10: Co-Development of Automatic Annotation for Machine Learning and Sensor Fusion Improvement System, Stefan Haag
11:10-11:40: Radar Perception for Automated Driving – Data and Methods, Ole Schumann
11:40-12:10: Perception Data Pipeline at Innoviz Technologies, Amir Day
12:10-12:30: [paper 1] The Oxford Road Boundaries Dataset, Tarlan Suleymanov*, Matthew Gadd, Daniele De Martini, Paul Newman
12:30-13:30 Lunch Break
13:30-13:50: [paper2] Unsupervised Joint Multi-Task Learning of Vision Geometry Tasks, Prabhash Kumar Jha*, Doychin Tsanev, Luka Lukic
13:50-14:10: [paper3] CFTrack: Center-based Radar and Camera Fusion for 3D Multi Object Tracking, Ramin Nabati, Landon Harris, Hairong Qi
14:10-14:30: [paper4] Machine learning based 3D object detection for navigation in unstructured environments, Gjorgji Nikolovski, Michael Reke*, Ingo Elsen, Stefan Schiffer
14:30-14:50: [paper5] Pruning CNNs for LiDAR-based Perception in Resource Constrained Environments, Manoj Vemparala*, Anmol Singh, Ahmed Mzid, Nael Fasfous, Alexander Frickenstein, Florian Mirus, Hans Joerg Voegel, Naveen Shankar Nagaraja, Walter Stechele
09:10-09:40: On Monocular Depth Estimation: (1) MonoDEVS ; (2) Multi-modal Co-training, Dr. Antonio M. López
09:40-10:10: Point-based recognition, Prof. Philipp Krähenbühl
10:10-10:40: Lidar Segmentation at Motional, Venice Liong
10:40-11:10: Co-Development of Automatic Annotation for Machine Learning and Sensor Fusion Improvement System, Stefan Haag
11:10-11:40: Radar Perception for Automated Driving – Data and Methods, Ole Schumann
11:40-12:10: Perception Data Pipeline at Innoviz Technologies, Amir Day
12:10-12:30: [paper 1] The Oxford Road Boundaries Dataset, Tarlan Suleymanov*, Matthew Gadd, Daniele De Martini, Paul Newman
12:30-13:30 Lunch Break
13:30-13:50: [paper2] Unsupervised Joint Multi-Task Learning of Vision Geometry Tasks, Prabhash Kumar Jha*, Doychin Tsanev, Luka Lukic
13:50-14:10: [paper3] CFTrack: Center-based Radar and Camera Fusion for 3D Multi Object Tracking, Ramin Nabati, Landon Harris, Hairong Qi
14:10-14:30: [paper4] Machine learning based 3D object detection for navigation in unstructured environments, Gjorgji Nikolovski, Michael Reke*, Ingo Elsen, Stefan Schiffer
14:30-14:50: [paper5] Pruning CNNs for LiDAR-based Perception in Resource Constrained Environments, Manoj Vemparala*, Anmol Singh, Ahmed Mzid, Nael Fasfous, Alexander Frickenstein, Florian Mirus, Hans Joerg Voegel, Naveen Shankar Nagaraja, Walter Stechele
14:50-15:00 BREAK
15:00-15:30: Modern methods of visual localization, Dr. Martin Humenberger
15:30-16:00: All-In-One Drive: A Large-Scale Comprehensive Perception Dataset with High-Density Long-Range Point Clouds, Xinshuo Weng
16:00-16:30: Offboard Perception for Autonomous Driving, Charles R Qi
16:30-17:00: Using Artificial Intelligence layer to transform high-resolution radar point cloud into insights for Autonomous Driving applications, Sani Ronen
17:00-17:30: Self-supervised 3D vision, Dr. Rareș Ambruș
17:30-17:45: Closing
15:00-15:30: Modern methods of visual localization, Dr. Martin Humenberger
15:30-16:00: All-In-One Drive: A Large-Scale Comprehensive Perception Dataset with High-Density Long-Range Point Clouds, Xinshuo Weng
16:00-16:30: Offboard Perception for Autonomous Driving, Charles R Qi
16:30-17:00: Using Artificial Intelligence layer to transform high-resolution radar point cloud into insights for Autonomous Driving applications, Sani Ronen
17:00-17:30: Self-supervised 3D vision, Dr. Rareș Ambruș
17:30-17:45: Closing
Workshop Organizers:
B Ravi Kiran, Navya, France
Senthil Yogamani, Valeo Vision Systems, Ireland
Victor Vaquero, Research Engineer, IVEX.ai
Patrick Perez, Valeo.AI, France
Bharanidhar Duraisamy, Daimler, Germany
Dan Levi, GM, Israel
Abhinav Valada, University of Freiburg, Germany
Lars Kunze, Oxford University, UK
Markus Enzweiler, Daimler, Germany
Ahmad El Sallab, Valeo AI Research, Egypt
Sumanth Chennupati, Wyze Labs, USA
Stefan Milz, Spleenlab.ai , Germany
Hazem Rashed, Valeo AI Research, Egypt
Jean-Emmanuel Deschaud, MINES ParisTech, France
Kuo-Chin Lien, Appen USA
Naveen Shankar Nagaraja, BMW Group, Munich
B Ravi Kiran, Navya, France
Senthil Yogamani, Valeo Vision Systems, Ireland
Victor Vaquero, Research Engineer, IVEX.ai
Patrick Perez, Valeo.AI, France
Bharanidhar Duraisamy, Daimler, Germany
Dan Levi, GM, Israel
Abhinav Valada, University of Freiburg, Germany
Lars Kunze, Oxford University, UK
Markus Enzweiler, Daimler, Germany
Ahmad El Sallab, Valeo AI Research, Egypt
Sumanth Chennupati, Wyze Labs, USA
Stefan Milz, Spleenlab.ai , Germany
Hazem Rashed, Valeo AI Research, Egypt
Jean-Emmanuel Deschaud, MINES ParisTech, France
Kuo-Chin Lien, Appen USA
Naveen Shankar Nagaraja, BMW Group, Munich
Posted in