Research Group Federico Tombari
Federico Tombari
PD Dr.
Collaborating PI
Federico Tombari
is Lecturer (Privatdozent) at the Chair of Computer Aided Medical Procedures & Augmented Reality at TU Munich. He is also a Director of Research at Google Zurich, Switzerland, where he leads an applied research team in Computer Vision and Machine Learning.
His research activity is focused on different aspects of computer vision and machine learning, with a focus on 3D computer vision (e.g. scene understanding, 3D object recognition, 3D reconstruction, SLAM). The fields of application of his research are mainly in robotics, augmented reality, autonomous driving and healthcare. A main focus is currently on unsupervised learning for visual data, Large Multimodal Models, (Neural) Radiance Fields, and scene graphs for scene understanding.
Team members @MCML
PostDocs
Nikolas Brasch
Dr.
→ Group Federico Tombari
Computer Aided Medical Procedures & Augmented Reality
Stefano Gasperini
Dr.
→ Group Federico Tombari
Computer Aided Medical Procedures & Augmented Reality
Shun-Cheng Wu
Dr.
→ Group Federico Tombari
Computer Aided Medical Procedures & Augmented Reality
PhD Students
Kunyi Li
→ Group Federico Tombari
Computer Aided Medical Procedures & Augmented Reality
Nils Morbitzer
→ Group Federico Tombari
Computer Aided Medical Procedures & Augmented Reality
Klara Reichard
→ Group Federico Tombari
Computer Aided Medical Procedures & Augmented Reality
Recent News @MCML
Publications @MCML
2026
DynaTok: Token-Based 4D Reconstruction from Partial Point Clouds.
ICML 2026 - 43rd International Conference on Machine Learning. Seoul, South Korea, Jul 06-11, 2026. To be published. Preprint available. URL GitHub
Future Dynamic 3D Reconstruction: A 3D World Model with Disentangled Ego-Motio.
ICML 2026 - 43rd International Conference on Machine Learning. Seoul, South Korea, Jul 06-11, 2026. To be published. Preprint available. URL GitHub
Featurising Pixels from Dynamic 3D Scenes with Linear In-Context Learners.
CVPR 2026 - IEEE/CVF Conference on Computer Vision and Pattern Recognition. Denver, CO, USA, Jun 03-07, 2026. To be published. Preprint available. arXiv GitHub
Learning 3D Scene Reconstruction From Nighttime Driving Videos.
IEEE Robotics and Automation Letters Early Access. Jun. 2026. DOI GitHub
OpenGaFF: Open-Vocabulary Gaussian Feature Field with Codebook Attention.
Preprint (May. 2026). arXiv
OracleGS: Grounding Generative Priors for Sparse-View Gaussian Splatting.
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
Transient LASSO: Transient Large-Scale Scene Reconstruction.
SIGGRAPH ASIA 2025 - 18th ACM SIGGRAPH Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia. Hong Kong, China, Dec 15-18, 2025. DOI
From Open-Vocabulary to Vocabulary-Free Semantic Segmentation.
Pattern Recognition Letters 198. Dec. 2025. DOI GitHub
Supplementary Material Transient LASSO: Transient Large-Scale Scene Reconstruction.
Preprint (Dec. 2025). PDF
Reasoning with Fewer Eyes: Efficient Visual Token Withdrawal for Multimodal Reasoning.
ER @NeurIPS 2025 - Workshop on Efficient Reasoning at the 39th Conference on Neural Information Processing Systems. San Diego, CA, USA, Nov 30-Dec 07, 2025. URL
MonoGSDF: Exploring Monocular Geometric Cues for Gaussian Splatting-Guided Implicit Surface Reconstruction.
Preprint (Nov. 2025). arXiv
Prior2Former - Evidential Modeling of Mask Transformers for Assumption-Free Open-World Panoptic Segmentation.
ICCV 2025 - IEEE/CVF International Conference on Computer Vision. Honolulu, Hawai’i, Oct 19-23, 2025. DOI
VoxNeRF: Bridging Voxel Representation and Neural Radiance Fields for Enhanced Indoor View Synthesis.
IROS 2025 - IEEE/RSJ International Conference on Intelligent Robots and Systems. Hangzhou, China, Oct 19-25, 2025. DOI
SING3R-SLAM: Submap-based Indoor Monocular Gaussian SLAM with 3D Reconstruction Priors.
Preprint (Oct. 2025). arXiv
Visibility-Aware Language Aggregation for Open-Vocabulary Segmentation in 3D Gaussian Splatting.
Preprint (Sep. 2025). arXiv
GALA: Guided Attention with Language Alignment for Open Vocabulary Gaussian Splatting.
Preprint (Aug. 2025). arXiv
VoxNeRF: Bridging Voxel Representation and Neural Radiance Fields for Enhanced Indoor View Synthesis.
IEEE Robotics and Automation Letters 10.6. Jun. 2025. DOI
Strategies Towards Reliable Scene Understanding for Autonomous Driving.
Dissertation TU München. Jan. 2025. URL
2024
SuperGSeg: Open-Vocabulary 3D Segmentation with Structured Super-Gaussians.
Preprint (Dec. 2024). arXiv
HouseCat6D -- A Large-Scale Multi-Modal Category Level 6D Object Perception Dataset with Household Objects in Realistic Scenarios.
CVPR 2024 - IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, WA, USA, Jun 17-21, 2024. DOI
2023
CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graph Diffusion.
NeurIPS 2023 - 37th Conference on Neural Information Processing Systems. New Orleans, LA, USA, Dec 10-16, 2023. DOI
©all images: LMU | TUM
2025-03-17 - Last modified: 2026-07-03