- 3D Adversarial Augmentations for Robust Out-of-Domain Predictions. International Journal of Computer Vision (IJCV) 132, 2024, 931–963 more…
- Re-Nerfing: Improving Novel Views Synthesis through Novel Views Synthesis. arXiv preprint, under review, 2024 more…
- Robust Monocular Depth Estimation under Challenging Conditions. IEEE/CVF International Conference on Computer Vision (ICCV), 2023 more…
- VoxNeRF: Bridging Voxel Representation and Neural Radiance Fields for Enhanced Indoor View Synthesis. arXiv preprint, under review, 2023 more…
- Segmenting Known Objects and Unseen Unknowns without Prior Knowledge. IEEE/CVF International Conference on Computer Vision (ICCV), 2023 more…
- 3D-VField: Adversarial Augmentation of Point Clouds for Domain Generalization in 3D Object Detection. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022 more…
- CertainNet: Sampling-free Uncertainty Estimation for Object Detection. IEEE Robotics and Automation Letters (RA-L), 2021 more…
- Panoster: End-to-end Panoptic Segmentation of LiDAR Point Clouds. IEEE Robotics and Automation Letters (RA-L), 2021 more…
- R4Dyn: Exploring Radar for Self-Supervised Monocular Depth Estimation of Dynamic Scenes. Proceedings of the IEEE International Conference on 3D Vision (3DV), 2021, 2021 more…
- Signal Clustering with Class-independent Segmentation. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2020 more…
- 3DQ: Compact Quantized Neural Networks for Volumetric Whole Brain Segmentation. Proceedings of the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2019 more…
Stefano Gasperini
Inaktiv: Der Benutzer ist in TUMonline nicht mehr aktiv!
Inactive: The user is not active in TUMonline anymore!
Inactive: The user is not active in TUMonline anymore!
Open Projects
Reach out for a MSc Thesis project on autonomous driving perception. Good prior knowledge of computer vision and deep learning is required.
Research Interests
- 3D Reconstruction
- Scene Understanding
- Autonomous Driving
- Reliability in Computer Vision
- Robustness
- Domain Generalization
Publications
As PostDoc
Research advisor for the following PhD candidates:
- Nils Morbitzer, already supervised him throughout his Master's studies at TUM
- Christian Kapeller, in collaboration with the Austrian Institute of Technology (AIT)
- Klara Reichard, in collaboration with BMW
- Changxuan Li, in collaboration with BMW
- Sen Wang, in collaboration with Huawei
- Giulia Rizzoli, visiting scholar from the University of Padova, Italy
This is partly supported by PD Dr. Federico Tombari. As a senior member of the Computer Vision Team and the CAMP Chair, tasks also involve supporting and coordinating some of the activities of the Chair, such as seeking new projects, funding opportunities, and collaborations with industry and other research partners, and coordinating a research group about reconstruction.
Curriculum Vitae
- 01/2024 - ongoing: PostDoc at TUM, Computer Vision, part-time.
- 10/2023 - ongoing: Co-Founder & CEO of VisualAIs, Computer Vision startup creating 3D renderings of products from smartphone images.
- 11/2019 - ongoing: PhD Candidate in Reliable 3D Scene Understanding for Autonomous Driving at TUM, supervised by PD Dr. Federico Tombari. PhD thesis submitted in December 2023.
- 11/2019 - 12/2022: PhD Researcher in Autonomous Driving at BMW, Unterschleißheim, Germany.
- 04/2019 - 10/2019: Master Thesis Student at Airbus, Manching, Germany.
- 04/2018 - 03/2019: Working Student Researcher at Airbus, Manching, Germany.
- 10/2017 - 11/2019: Master in Informatics at TUM.
- 10/2016 - 09/2017: Software Developer at Prometeia / Modis, Bologna, Italy.
- 09/2013 - 10/2016: Bachelor in Computer Engineering at the University of Bologna, Italy.
- 09/2015 - 06/2016: Exchange Student at the University of California Santa Cruz (UCSC), California, USA.
Scholarships and Awards
- Outstanding Reviewer at ECCV 2024 (top 2.71% of 7293 reviewers).
- Outstanding Reviewer at ICCV 2023 (top 1.87% of 6990 reviewers).
- Deutschlandstipendium holder, merit-based Scholarship program (top 1% of students in Germany), for the second consecutive year, sponsored by the German government and Airbus (10.2018-09.2019).
- Deutschlandstipendium holder, merit-based Scholarship program (top 1% of students in Germany), sponsored by the German government and a TUM association (10.2017-09.2018).
- Graduated “summa cum Laude” ("110 e Lode") in Computer Engineering, University of Bologna, Italy (07.10.2016).
- Provost’s Commendations for Excellence, University of Bologna, Italy (06.2015).
Teaching
Teaching assistant in the following courses:
- Summer 2023: Seminar on Recent Trends in 3D Computer Vision and Deep Learning
- Winter 2022/2023: Lab Course on 3D Computer Vision
- Winter 2022/2023: Seminar on Modern Computer Vision Methods
- Summer 2022: Lab Course on Advanced Topics in 3D Computer Vision
- Summer 2022: Seminar on Recent Trends in 3D Computer Vision and Deep Learning
- Winter 2021/2022: Lab Course on 3D Computer Vision.
- Summer 2021: Seminar on Computer Vision and Deep Learning for Autonomous Driving.
- Winter 2020/2021: Seminar on Computer Vision and Deep Learning for Autonomous Driving.
- Summer 2020: Lab Course on Perception and Learning in Robotics and Augmented Reality.
- Winter 2019/2020: Seminar on Computer Vision and Deep Learning for Autonomous Driving.
Student Projects
Supervised the following MSc student projects (end):
- MSc Thesis - Neural Radiance Fields (NeRF) in highly sparse settings - Nils Morbitzer (2024).
- Guided Research - Time-consistent generic object pose estimation - Tarlan Bakirli (2023).
- MSc Thesis - Weakly Supervised Semantic Segmentation for RGB-D Data, Focus on Contrastive Learning and Pseudo Labeling - Mert Kiray - co-supervision with Lennart Bastian (2023).
- MSc Thesis - Weakly Supervised Semantic Segmentation for RGB-D Data, Focus on Robustness and Oversegmentation - Merve Karali - co-supervision with Lennart Bastian (2023).
- MSc Thesis - Self-supervised Segmentation for LiDAR Point Clouds - Philipp Nikutta - co-supervision with Lennart Bastian (2023).
- IDP - Improving Robustness of Self-supervised Monocular Depth Estimation Methods - Nils Morbitzer (2023).
- MSc Thesis - Multi-modal Panoptic Segmentation for Autonomous Driving - Christopher Heumann - TUM and BMW sides (2022).
- MSc Thesis - Open-Set Panoptic Segmentation for Autonomous Driving - Frithjof Winkelmann - TUM and BMW sides (2022).
- MSc Thesis - Uncertainty Estimation for Object Detection in Autonomous Driving - Jan Haug - TUM and BMW sides (2021).
- MSc Thesis - Enhancing Monocular Depth Estimation for Autonomous Driving with Sparse Radar Data - Patrick Koch - TUM and BMW sides (2021).
- MSc Thesis - Evaluation of Semantic Segmentation Methods for LiDAR Point Clouds - Florian Hartmann - BMW side (2021).
Additionally supervised practical semester projects through the lab courses (Teaching Section). Topics include autonomous driving perception and 3D reconstruction.
Professional Services
Reviewed for the following conferences and journals:
- CVPR: IEEE/CVF Conference on Computer Vision and Pattern Recognition
- ICCV: IEEE/CVF International Conference on Computer Vision,
Outstanding Reviewer at ICCV 2023 (top 1.87% of 6990 reviewers). - ECCV: Springer European Conference on Computer Vision
Outstanding Reviewer at ECCV 2024 (top 2.71% of 7293 reviewers). - IJCV: Springer International Journal of Computer Vision
- NeurIPS: Conference on Neural Information Processing Systems.
- RA-L: IEEE Robotics and Automation Letters
- ICRA: IEEE International Conference on Robotics and Automation
- IROS: IEEE International Conference on Intelligent Robots and Systems
- PR: Elsevir Pattern Recognition, journal
- MedIA: Elsevir Medical Image Analysis Journal
- MICCAI (indirectly): Springer International Conference on Medical Image Computing and Computer Assisted Intervention