Articles listed in chronological order:
Hoi! A Multimodal Dataset for Force-Grounded, Cross-View Articulated Manipulation
CVPR 2026
BibTex
- @inproceedings{engelbracht2026hoi,
title={Hoi! A Multimodal Dataset for Force-Grounded, Cross-View Articulated Manipulation},
author={Engelbracht, Tim and Zurbr{\"u}gg, Ren{\'e} and Wohlrapp, M. and B{\"u}chner, M. and Valada, A. and Blum, Hermann and Pollefeys, Marc and Bauer, Zuria},
booktitle={CVPR},
year={2026}
}
FunFact: Building Probabilistic Functional 3D Scene Graphs via Factor-Graph Reasoning
CVPR 2026
BibTex
- @inproceedings{fu2026funfact,
title={FunFact: Building Probabilistic Functional 3D Scene Graphs via Factor-Graph Reasoning},
author={Fu, Zhengyu and Zurbr{\"u}gg, Ren{\'e} and Qu, Kaixian and Pollefeys, Marc and Hutter, Marco and Blum, Hermann and Bauer, Zuria},
booktitle={CVPR},
year={2026}
}
Articulated 3D Scene Graphs for Open-World Mobile Manipulation
Under Submission
BibTex
- @article{buchner2026articulated,
title={Articulated 3D Scene Graphs for Open-World Mobile Manipulation},
author={B{\"u}chner, M. and R{\"o}fer, A. and Engelbracht, Tim and Welschehold, T. and Bauer, Zuria and Blum, Hermann and others},
journal={arXiv preprint arXiv:2602.16356},
year={2026}
}
LeAD-M3D: Leveraging Asymmetric Distillation for Real-time Monocular 3D Detection
Under Submission
BibTex
- @article{meier2025lead,
title={LeAD-M3D: Leveraging Asymmetric Distillation for Real-time Monocular 3D Detection},
author={Meier, J. and Michel, J. and Dhaouadi, O. and Yang, Y.H. and Reich, C. and Bauer, Zuria and Roth, S. and others},
journal={arXiv preprint arXiv:2512.05663},
year={2025}
}
3D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detection
ICCV 2025
BibTex
- @inproceedings{yang2025mood,
title={3D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detection},
author={Yang, Yung-Hsu and Piccinelli, Luigi and Segu, Mattia and Li, Siyuan and Huang, Rui and Fu, Yuqian and Pollefeys, Marc and Blum, Hermann and Bauer, Zuria},
booktitle={ICCV},
year={2025}
}
Video Perception Models for 3D Scene Synthesis
NeurIPS 2025
BibTex
- @inproceedings{huang2025video,
title={Video Perception Models for 3D Scene Synthesis},
author={Huang, R. and Zhai, G. and Bauer, Zuria and Pollefeys, Marc and Tombari, F. and Guibas, L. and Huang, G. and others},
booktitle={NeurIPS},
year={2025}
}
MonoTracker: Monocular RGB-Only 6D Tracking of Unknown Objects
BMVC 2025
BibTex
- @inproceedings{deng2025monotracker,
title={MonoTracker: Monocular RGB-Only 6D Tracking of Unknown Objects},
author={Deng, Z. and Tan, S. and Bauer, Zuria and Barath, D. and Pollefeys, Marc},
booktitle={BMVC},
year={2025}
}
AIDEN: Design and Pilot Study of an AI Assistant for the Visually Impaired
arXiv 2025
BibTex
- @article{marquez2025aiden,
title={AIDEN: Design and Pilot Study of an AI Assistant for the Visually Impaired},
author={Marquez-Carpintero, L. and Gomez-Donoso, Francisco and Bauer, Zuria and Dominguez-Dager, Bessie and others},
journal={arXiv preprint arXiv:2511.06080},
year={2025}
}
SpotLight: Robotic Scene Understanding through Interaction and Affordance Detection
Humanoids 2025
BibTex
- @inproceedings{engelbracht2025spotlight,
title={SpotLight: Robotic Scene Understanding through Interaction and Affordance Detection},
author={Engelbracht, Tim and Zurbr{\"u}gg, Ren{\'e} and Pollefeys, Marc and Blum, Hermann and Bauer, Zuria},
booktitle={IEEE-RAS Humanoids},
year={2025}
}
Lost and Found: Updating Dynamic 3D Scene Graphs from Egocentric Observations
IROS 2025
BibTex
- @article{behrens2025lost,
title={Lost \& found: Tracking changes from egocentric observations in 3d dynamic scene graphs},
author={Behrens, Tjark and Zurbr{\"u}gg, Ren{\'e} and Pollefeys, Marc and Bauer, Zuria and Blum, Hermann},
journal={IEEE Robotics and Automation Letters},
year={2025},
publisher={IEEE}
}
CroCoDL: Cross-device Collaborative Dataset for Localization
CVPR 2025
BibTex
- @inproceedings{blum2025crocodl,
title={CroCoDL: Cross-device Collaborative Dataset for Localization},
author={Blum, Hermann and Mercurio, Alessandro and O'Reilly, Joshua and Engelbracht, Tim and Dusmanu, Mihai and Pollefeys, Marc and Bauer, Zuria},
booktitle={CVPR},
pages={27424--27434},
year={2025}
}
Spot-On: A Mixed Reality Interface for Multi-Robot Cooperation
CVPR 2025 (Workshop on Computer Vision for Mixed Reality)
BibTex
- @article{engelbracht2025spot,
title={Spot-On: A Mixed Reality Interface for Multi-Robot Cooperation},
author={Engelbracht, Tim and Lukovic, Petar and Behrens, Tjark and Lascheit, Kai and Zurbr{\"u}gg, Ren{\'e} and Pollefeys, Marc and Blum, Hermann and Bauer, Zuria},
journal={arXiv preprint arXiv:2505.22539},
year={2025}
}
MR. NAVI: Mixed-Reality Navigation Assistant for the Visually Impaired
CVPR 2025 (Workshop on Computer Vision for Mixed Reality)
BibTex
- @article{pfitzer2025mr,
title={MR. NAVI: Mixed-Reality Navigation Assistant for the Visually Impaired},
author={Pfitzer, Nicolas and Zhou, Yifan and Poggensee, Marco and Kurtulus, Defne and Dominguez-Dager, Bessie and Dusmanu, Mihai and Pollefeys, Marc and Bauer, Zuria},
journal={arXiv preprint arXiv:2506.05369},
year={2025}
}
HoloSpot: Intuitive Object Manipulation via Mixed Reality Drag-and-Drop
Under Submission
BibTex
- @misc{garcia2024holospot,
title={HoloSpot: Intuitive Object Manipulation via Mixed Reality Drag-and-Drop},
author={Pablo Soler Garcia and Petar Lukovic and Lucie Reynaud and Andrea Sgobbi and Federica Bruni and Martin Brun and Marc Z{\"u}nd and Riccardo Bollati and Marc Pollefeys and Hermann Blum and Zuria Bauer},
year={2024},
eprint={2410.11110},
archivePrefix={arXiv},
primaryClass={cs.RO},
url={https://arxiv.org/abs/2410.11110}
}
MaRINeR: Enhancing Novel Views by Matching Rendered Images with Nearby References
ECCV 2024
BibTex
- @inproceedings{bosiger2024mariner,
title={MaRINeR: Enhancing Novel Views by Matching Rendered Images with Nearby References},
author={B{\"o}siger, Lukas and Dusmanu, Mihai and Pollefeys, Marc and Bauer, Zuria},
booktitle={ECCV},
pages={76--94},
year={2024}
}
Spot-Compose: A Framework for Open-Vocabulary Object Retrieval and Drawer Manipulation in Point Clouds
ICRA 2024 (Workshop on Mobile Manipulation and Embodied Intelligence)
BibTex
- @inproceedings{lemke2024spotcompose,
title={Spot-Compose: A Framework for Open-Vocabulary Object Retrieval and Drawer Manipulation in Point Clouds},
author={Oliver Lemke and Zuria Bauer and Ren{\'e} Zurbr{\"u}gg and Marc Pollefeys and Francis Engelmann and Hermann Blum},
booktitle={Workshop on Mobile Manipulation and Embodied Intelligence at ICRA},
year={2024}
}
NeRFmentation: NeRF-based Augmentation for Monocular Depth Estimation
ECCV 2024 (Workshop on Synthetic Data for Computer Vision)
BibTex
- @article{feldmann2024nerfmentation,
title={NeRFmentation: NeRF-based Augmentation for Monocular Depth Estimation},
author={Feldmann, Casimir and Siegenheim, Niall and Hars, Nikolas and Rabuzin, Lovro and Ertugrul, Mert and Wolfart, Luca and Pollefeys, Marc and Bauer, Zuria and Oswald, Martin R},
journal={arXiv preprint arXiv:2401.03771},
year={2024}
}
Monocular Depth Estimation: Datasets, Methods, and Applications
PhD Thesis
BibTex
- @phdthesis{bauer2021monocular,
title={Monocular Depth Estimation: Datasets, Methods, and Applications},
author={Bauer, Zuria},
school={Universidad de Alicante},
year={2021}
}
NVS-MonoDepth: Improving Monocular Depth Prediction with Novel View Synthesis
3DV 2021
BibTex
- @inproceedings{bauer2021nvs,
title={NVS-MonoDepth: Improving Monocular Depth Prediction with Novel View Synthesis},
author={Bauer, Zuria and Li, Zuoyue and Orts-Escolano, Sergio and Cazorla, Miguel and Pollefeys, Marc and Oswald, Martin R},
booktitle={3DV},
pages={848--858},
year={2021}
}
Enhancing perception for the visually impaired with deep learning techniques and low-cost wearable sensors
Pattern Recognition Letters 2020
BibTex
- @article{bauer2020enhancing,
title={Enhancing perception for the visually impaired with deep learning techniques and low-cost wearable sensors},
author={Bauer, Zuria and Dominguez, Alejandro and Cruz, Edmanuel and Gomez-Donoso, Francisco and Orts-Escolano, Sergio and Cazorla, Miguel},
journal={Pattern Recognition Letters},
volume={137},
pages={27--36},
year={2020}
}
COMBAHO: A deep learning system for integrating brain injury patients in society
Pattern Recognition Letters 2020
BibTex
- @article{garcia2020combaho,
title={COMBAHO: A deep learning system for integrating brain injury patients in society},
author={Garcia-Rodriguez, Jose and Gomez-Donoso, Francisco and Oprea, Sergiu and Garcia-Garcia, Alberto and Cazorla, Miguel and Orts-Escolano, Sergio and Bauer, Zuria and Castro-Vargas, John and Escalona, Felix and Ivorra-Piqueres, David and others},
journal={Pattern Recognition Letters},
volume={137},
pages={80--90},
year={2020}
}
UASOL, a large-scale high-resolution outdoor stereo dataset
Scientific Data 2019
BibTex
- @article{bauer2019uasol,
title={UASOL, a large-scale high-resolution outdoor stereo dataset},
author={Bauer, Zuria and Gomez-Donoso, Francisco and Cruz, Edmanuel and Orts-Escolano, Sergio and Cazorla, Miguel},
journal={Scientific Data},
volume={6},
number={1},
pages={1--14},
year={2019}
}
Refining the Fusion of Pepper Robot and Estimated Depth Maps Method for Improved 3D Perception
IEEE Access 2019
BibTex
- @article{bauer2019refining,
title={Refining the fusion of pepper robot and estimated depth maps method for improved 3d perception},
author={Bauer, Zuria and Escalona, Felix and Cruz, Edmanuel and Cazorla, Miguel and Gomez-Donoso, Francisco},
journal={IEEE Access},
volume={7},
pages={185076--185085},
year={2019}
}
Geoffrey: an automated schedule system on a social robot for the intellectually challenged
Computational Intelligence and Neuroscience 2018
BibTex
- @article{cruz2018geoffrey,
title={Geoffrey: An automated schedule system on a social robot for the intellectually challenged},
author={Cruz, Edmanuel and Escalona, F{\'e}lix and Bauer, Zuria and Cazorla, Miguel and Garcia-Rodriguez, Jose and Martinez-Martin, Ester and Rangel, Jos{\'e} Carlos and Gomez-Donoso, Francisco},
journal={Computational Intelligence and Neuroscience},
volume={2018},
publisher={Hindawi}
}
Semantic Localization of a Robot in a Real Home
Workshop of Physical Agents 2018
BibTex
- @inproceedings{cruz2018semantic,
title={Semantic localization of a robot in a real home},
author={Cruz, Edmanuel and Bauer, Zuria and Rangel, Jos{\'e} Carlos and Cazorla, Miguel and Gomez-Donoso, Francisco},
booktitle={Workshop of Physical Agents},
pages={3--15},
year={2018}
}
Improving the 3D Perception of the Pepper Robot Using Depth Prediction from Monocular Frames
Workshop of Physical Agents 2018
BibTex
- @inproceedings{bauer2018improving,
title={Improving the 3D perception of the pepper robot using depth prediction from monocular frames},
author={Bauer, Zuria and Escalona, Felix and Cruz, Edmanuel and Cazorla, Miguel and Gomez-Donoso, Francisco},
booktitle={Workshop of Physical Agents},
pages={132--146},
year={2018}
}
Finding the Place: How to Train and Use Convolutional Neural Networks for a Dynamically Learning Robot
IJCNN 2018
BibTex
- @inproceedings{cruz2018finding,
title={Finding the place: how to train and use convolutional neural networks for a dynamically learning robot},
author={Cruz, Edmanuel and Rangel, Jos{\'e} Carlos and Gomez-Donoso, Francisco and Bauer, Zuria and Cazorla, Miguel and Garc{\'\i}a-Rodr{\'\i}guez, Jos{\'e}},
booktitle={IJCNN},
pages={1--8},
year={2018}
}