Dr. Sk Aziz Ali

I have embarked a new post-doctoral position at the Augmented Vision research group of German Research Center for Artificial Intelligence (DFKI GmbH), starting from November 2023. Previously, I was a postdoctoral researcher at the Computer Vision Imaging and Machine Intelligence (CVI2) research group led by Prof. Dr. Djamila Aouada at the University of Luxembourg. Prior to joining CVI2 group, I received my PhD and M.Sc in Computer Science from the University of Kaiserslauter-Landau (RPTU), Germany. My PhD and Masters study advisors were Prof. Dr. Didier Stricker and Prof. Dr. Hans Hagen.

Research

I did my master thesis, titled as- “Visualization of FEM data for FRP materials”, from DLR (German Aerospace) where he prototyped a visually based Fiber Reinforced Plastic(FRP) material failure analysis tool to help structure designing engineers analyzing the strength of aircraft components. My primary emphasis during doctoral research program with the German Research Center for Artificial Intelligence was “Fast Robust Rigid and Non-rigid Registration for Globally Consistent 3D Scene and Shape Reconstruction”. My research interest combines – 3D Computer Vision, Deep Learning and Machine Learning Methods for Resource-Constrained and Explainable AI, Intelligent Perception for Autonomous Driving Systems using Vision-Language models, Point Set Registration, Globally Consistent Scene and Shape Reconstruction, NLP + Geometric Deep Learning for Scan-to-CAD Reverse Engineering, and Embodied AI on the Edge.

Open Position

I have an open position for a PhD student, options to collaborate on the topics under Intelligent Perception for Autonomous Driving Systems using Vision-Language/Large-Language models and Embodied+Explainable AI on the Edge.
If you are interested in doing thesis/internship/HiWi(i.e., student research) job on topics under general framework of (1) Autonomous Driving Systems (2) Vision-Language/Large-Language models, and (3) Embodied+Explainable AI on the Edge, do not hesitate to contact me.

news

Apr 21, 2024	I am delighted to announce that our highlight paper CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance Guided Attention is accepted at the IEEE/CVF CVPR 2024.
Nov 15, 2023	I am deligted to post that our research group at AV-DFKI showed strong presence (highlighted in the DFKI press rlease) with no less than Two Papers are accepted at the IEEE/CVF ICCV 2023.
Sep 30, 2023	Two papers are accepted at the IEEE/CVF ICCV 2023 - (1) DELO: Deep Evidential LiDAR Odometry using Partial Optimal Transport and (2) SHARP Challenge 2023: Solving CAD History and pArameters Recovery from Point clouds and 3D scans. Overview, Datasets, Metrics, and Baselines.
Aug 19, 2023	Our paper DELO: Deep Evidential LiDAR Odometry Using Partial Optimal Transport has been accepted for publication at IEEE CVF International Conference on Computer Vision Workshop ICCV 2023. (paper, project-page, code).
Aug 19, 2023	I am co-organizing the The 4th edition of the SHARP Workshop and challenge in conjunction with ICCV 2023. The registrations for this workshop are open. Join the challenge here! with the oppotunity to win a prize money of🔸 8k€ sponsored by Artec 3D 🏆

selected publications

DELO: Deep Evidential LiDAR Odometry using Partial Optimal Transport

Sk Aziz Ali, Djamila Aouada, Gerd Reis, and Didier Stricker

In In IEEE CVF International Conference on Computer Vision (ICCV), 2023

arXiv Bib HTML Code Poster

@inproceedings{AliDELO_ICCV23,
  title = {DELO: Deep Evidential LiDAR Odometry using Partial Optimal Transport},
  author = {Ali, Sk Aziz and and Aouada, Djamila and Reis, Gerd and Stricker, Didier},
  booktitle = {In IEEE CVF International Conference on Computer Vision (ICCV)},
  year = {2023},
  organization = {IEEE},
}

SHARP Challenge 2023: Solving CAD History and pArameters Recovery from Point clouds and 3D scans. Overview, Datasets, Metrics, and Baselines

Dimitrios Mallis, Sk Aziz Ali, Elona Dupont, Kseniya Cherenkova, Ahmet Serdar Karadeniz, Mohammed Sadil Khan Anis Kacem, Gleb Gusev, and Djamila Aouada

In In IEEE/CVF International Conference on Computer Vision (ICCV), 2023

arXiv Bib HTML Poster

@inproceedings{AliSHARP_ICCV23,
  title = {SHARP Challenge 2023: Solving CAD History and pArameters Recovery from Point clouds and 3D scans. Overview, Datasets, Metrics, and Baselines},
  author = {Mallis, Dimitrios and Ali, Sk Aziz and Dupont, Elona and Cherenkova, Kseniya and Karadeniz, Ahmet Serdar and Kacem, Mohammed Sadil Khan Anis and Gusev, Gleb and Aouada, Djamila},
  booktitle = {In IEEE/CVF International Conference on Computer Vision (ICCV)},
  year = {2023},
  organization = {IEEE},
}

Gravitational Approach for Point Set Registration

Vladislav Golyanik, Sk Aziz Ali, and Didier Stricker

In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2016

Bib PDF Supp Code Poster

@inproceedings{Golyanik_2016_CVPR,
  author = {Golyanik, Vladislav and Ali, Sk Aziz and Stricker, Didier},
  title = {Gravitational Approach for Point Set Registration},
  booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  month = jun,
  year = {2016},
  publisher = {IEEE},
}

Nrga: Gravitational approach for non-rigid point set registration

Sk Aziz Ali, Vladislav Golyanik, and Didier Stricker

In 2018 International Conference on 3D Vision (3DV), Jun 2018

Bib HTML PDF Code Poster

@inproceedings{ali2018nrga,
  title = {Nrga: Gravitational approach for non-rigid point set registration},
  author = {Ali, Sk Aziz and Golyanik, Vladislav and Stricker, Didier},
  booktitle = {2018 International Conference on 3D Vision (3DV)},
  pages = {756--765},
  year = {2018},
  organization = {IEEE},
}

TSCom-Net: Coarse-to-Fine 3D Textured Shape Completion Network

Ahmet Serdar Karadeniz, Sk Aziz Ali, Anis Kacem, Elona Dupont, and Djamila Aouada

In Computer Vision – ECCV 2022 Workshops, Jun 2022

arXiv Bib HTML Code Slides

@inproceedings{TScomNetECCVW2021,
  author = {Karadeniz, Ahmet Serdar and Ali, Sk Aziz and Kacem, Anis and Dupont, Elona and Aouada, Djamila},
  editor = {Karlinsky, Leonid and Michaeli, Tomer and Nishino, Ko},
  title = {TSCom-Net: Coarse-to-Fine 3D Textured Shape Completion Network},
  booktitle = {Computer Vision -- ECCV 2022 Workshops},
  year = {2022},
  publisher = {Springer Nature Switzerland},
  address = {Cham},
  pages = {289--306},
  isbn = {978-3-031-25072-9},
}

Cadops-net: Jointly learning cad operation types and steps from boundary-representations

Elona Dupont, Kseniya Cherenkova, Anis Kacem, Sk Aziz Ali, Ilya Arzhannikov, Gleb Gusev, and Djamila Aouada

In International Conference on 3D Vision (3DV), Jun 2022

arXiv Bib HTML PDF Supp Poster Slides

@inproceedings{dupont2022cadops,
  title = {Cadops-net: Jointly learning cad operation types and steps from boundary-representations},
  author = {Dupont, Elona and Cherenkova, Kseniya and Kacem, Anis and Ali, Sk Aziz and Arzhannikov, Ilya and Gusev, Gleb and Aouada, Djamila},
  booktitle = {International Conference on 3D Vision (3DV)},
  pages = {114--123},
  year = {2022},
  organization = {IEEE},
}

RPSRNet: End-to-End Trainable Rigid Point Set Registration Network using Barnes-Hut 2^D-Tree Representation

Sk Aziz Ali, Kerem Kahraman, Gerd Reis, and Didier Stricker

In IEEE/CVF Computer Vision and Pattern Recognition (CVPR), Jun 2021

arXiv Bib HTML Supp Poster Slides

@inproceedings{RPSRNet2021Ali,
  title = {RPSRNet: End-to-End Trainable Rigid Point Set Registration Network using Barnes-Hut 2^D-Tree Representation},
  author = {Ali, Sk Aziz and Kahraman, Kerem and Reis, Gerd and Stricker, Didier},
  booktitle = {IEEE/CVF Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
  organization = {IEEE},
}