Research Group Riccardo Marin
Riccardo Marin
Prof. Dr.
Core PI
Riccardo Marin
is a resarcher at Computer Vision Group, and Interim Professor at the Chair of Machine Learning for Robotics at TU Munich.
His research focuses on Computer Vision, Machine Learning, and Virtual Humans, aiming to provide Artificial Intelligence with a sense of the three-dimensional World that aligns with human perception. In particular, he is interested in finding analogies between objects, recovering corresponding geometrical and semantical points, with a particular interest in analyzing 3D human data. Methodologically, his research appropriates and extends approaches from spectral shape analysis, 3D signal processing, and geometric deep learning.
Recent News @MCML
Publications @MCML
2026
[10]
V. Ehm • D. Cao • R. Marin • D. Scholz • W. Wang • F. Bernard • D. Cremers
Teaching DINOv3 About Partial 3D Geometry: A Self-Supervised Geometry-Aware Approach.
CVPR 2026 - IEEE/CVF Conference on Computer Vision and Pattern Recognition. Denver, CO, USA, Jun 03-07, 2026. To be published. Preprint available. URL
Teaching DINOv3 About Partial 3D Geometry: A Self-Supervised Geometry-Aware Approach.
CVPR 2026 - IEEE/CVF Conference on Computer Vision and Pattern Recognition. Denver, CO, USA, Jun 03-07, 2026. To be published. Preprint available. URL
[9]
M. Gao • S. J. Hu-Chen • C. Deng • R. Marin • L. Guibas • D. Cremers
RINO: Rotation-Invariant Non-Rigid Correspondences.
CVPR 2026 - IEEE/CVF Conference on Computer Vision and Pattern Recognition. Denver, CO, USA, Jun 03-07, 2026. To be published. Preprint available. arXiv
RINO: Rotation-Invariant Non-Rigid Correspondences.
CVPR 2026 - IEEE/CVF Conference on Computer Vision and Pattern Recognition. Denver, CO, USA, Jun 03-07, 2026. To be published. Preprint available. arXiv
[8]
A. Zhuravlev • L. Bastian • D. Cao • N. E. Amrani • P. Roetzer • V. Ehm • R. Marin • H. Nishizawa • S. Morishima • C. Theobalt • N. Navab • D. Cremers • F. Bernard • Z. Lähner • V. Golyanik
Non-Rigid 3D Shape Correspondences: From Foundations to Open Challenges and Opportunities.
EUROGRAPHICS 2026 - 47th Annual Conference of the European Association for Computer Graphics. Aachen, Germany, May 04-08, 2026. To be published. Preprint available. arXiv GitHub
Non-Rigid 3D Shape Correspondences: From Foundations to Open Challenges and Opportunities.
EUROGRAPHICS 2026 - 47th Annual Conference of the European Association for Computer Graphics. Aachen, Germany, May 04-08, 2026. To be published. Preprint available. arXiv GitHub
[7]
L. Sang • Z. Canfes • D. Cao • R. Marin • F. Bernard • D. Cremers
TwoSquared: 4D Generation from 2D Image Pairs.
3DV 2026 - 13th International Conference on 3D Vision. Vancouver, Canada, Mar 20-23, 2026. To be published. Preprint available. URL
TwoSquared: 4D Generation from 2D Image Pairs.
3DV 2026 - 13th International Conference on 3D Vision. Vancouver, Canada, Mar 20-23, 2026. To be published. Preprint available. URL
[6]
J. Meier • F. Günther • R. Marin • O. Dhaouadi • J. Kaiser • D. Cremers
IDEAL-M3D: Instance Diversity-Enriched Active Learning for Monocular 3D Detection.
WACV 2026 - IEEE/CVF Winter Conference on Applications of Computer Vision. Tucson, AZ, USA, Mar 06-10, 2026. To be published. Preprint available. arXiv
IDEAL-M3D: Instance Diversity-Enriched Active Learning for Monocular 3D Detection.
WACV 2026 - IEEE/CVF Winter Conference on Applications of Computer Vision. Tucson, AZ, USA, Mar 06-10, 2026. To be published. Preprint available. arXiv
2025
[5]
O. Dhaouadi • R. Marin • J. Meier • J. Kaiser • D. Cremers
OrthoLoC: UAV 6-DoF Localization and Calibration Using Orthographic Geodata.
NeurIPS 2025 - 39th Conference on Neural Information Processing Systems. San Diego, CA, USA, Nov 30-Dec 07, 2025. Oral Presentation. URL GitHub
OrthoLoC: UAV 6-DoF Localization and Calibration Using Orthographic Geodata.
NeurIPS 2025 - 39th Conference on Neural Information Processing Systems. San Diego, CA, USA, Nov 30-Dec 07, 2025. Oral Presentation. URL GitHub
[4]
R. Hartwig • D. Muhle • R. Marin • D. Cremers
GECO: Geometrically Consistent Embedding with Lightspeed Inference.
ICCV 2025 - IEEE/CVF International Conference on Computer Vision. Honolulu, Hawai’i, Oct 19-23, 2025. DOI GitHub
GECO: Geometrically Consistent Embedding with Lightspeed Inference.
ICCV 2025 - IEEE/CVF International Conference on Computer Vision. Honolulu, Hawai’i, Oct 19-23, 2025. DOI GitHub
[3]
I. A. Petrov • R. Marin • J. Chibane • G. Pons-Moll
TriDi: Trilateral Diffusion of 3D Humans, Objects, and Interactions.
ICCV 2025 - IEEE/CVF International Conference on Computer Vision. Honolulu, Hawai’i, Oct 19-23, 2025. DOI GitHub
TriDi: Trilateral Diffusion of 3D Humans, Objects, and Interactions.
ICCV 2025 - IEEE/CVF International Conference on Computer Vision. Honolulu, Hawai’i, Oct 19-23, 2025. DOI GitHub
[2]
I. A. Petrov • V. Guzov • R. Marin • E. Aksan • X. Chen • D. Cremers • T. Beeler • G. Pons-Moll
ECHO: Ego-Centric modeling of Human-Object interactions.
Preprint (Aug. 2025). arXiv
ECHO: Ego-Centric modeling of Human-Object interactions.
Preprint (Aug. 2025). arXiv
[1]
L. Sang • Z. Canfes • D. Cao • R. Marin • F. Bernard • D. Cremers
4Deform: Neural Surface Deformation for Robust Shape Interpolation.
CVPR 2025 - IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville, TN, USA, Jun 11-15, 2025. DOI
4Deform: Neural Surface Deformation for Robust Shape Interpolation.
CVPR 2025 - IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville, TN, USA, Jun 11-15, 2025. DOI
©all images: LMU | TUM
Back to Top
2025-07-16 - Last modified: 2026-06-02