Christopher Wewer (PhD Student)

MSc Christopher Wewer

Address: Max-Planck-Institut für Informatik
Saarland Informatics Campus
Campus E1 4
66123 Saarbrücken
Location: E1 4 - 612
Phone: +49 681 9325 2121
Fax: +49 681 9325 2099
E-mail: Get email via email

Publications

2025

Conference paper

K. Raj, C. Wewer, R. Yunus, E. Ilg, and J. E. Lenssen

“Spurfies: Sparse-view Surface Reconstruction using Local Geometry Priors,” in 3DV 2025, 12th International Conference on 3D Vision, Singapore, 2025.

@inproceedings{Raj3DV25,
TITLE = {Spurfies: {S}parse-view Surface Reconstruction using Local Geometry Priors},
AUTHOR = {Raj, Kevin and Wewer, Christopher and Yunus, Raza and Ilg, Eddy and Lenssen, Jan Eric},
LANGUAGE = {eng},
ISBN = {979-8-3315-3851-4},
DOI = {10.1109/3DV66043.2025.00012},
PUBLISHER = {IEEE},
YEAR = {2025},
MARGINALMARK = {$\bullet$},
DATE = {2025},
BOOKTITLE = {3DV 2025, 12th International Conference on 3D Vision},
PAGES = {64--77},
ADDRESS = {Singapore},
}

Endnote

%0 Conference Proceedings
%A Raj, Kevin
%A Wewer, Christopher
%A Yunus, Raza
%A Ilg, Eddy
%A Lenssen, Jan Eric
%+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
External Organizations
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
%T Spurfies: Sparse-view Surface Reconstruction using Local Geometry Priors : 
%G eng
%U http://hdl.handle.net/21.11116/0000-0010-8FAB-D
%R 10.1109/3DV66043.2025.00012
%D 2025
%B 12th International Conference on 3D Vision
%Z date of event: 2025-03-25 - 2025-03-28
%C Singapore
%B 3DV 2025
%P 64 - 77
%I IEEE
%@ 979-8-3315-3851-4

Conference paper

M. Asim, C. Wewer, T. Wimmer, B. Schiele, and J. E. Lenssen

“MEt3R: Measuring Multi-View Consistency in Generated Images,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2025), Nashville, TN, USA, 2025.

@inproceedings{Asim_CVPR25,
TITLE = {{MEt3R}: {M}easuring Multi-View Consistency in Generated Images},
AUTHOR = {Asim, Mohammad and Wewer, Christopher and Wimmer, Thomas and Schiele, Bernt and Lenssen, Jan Eric},
LANGUAGE = {eng},
ISBN = {979-8-3315-4364-8},
DOI = {10.1109/CVPR52734.2025.00566},
PUBLISHER = {IEEE},
YEAR = {2025},
MARGINALMARK = {$\bullet$},
DATE = {2025},
BOOKTITLE = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2025)},
PAGES = {6034--6044},
ADDRESS = {Nashville, TN, USA},
}

Endnote

%0 Conference Proceedings
%A Asim, Mohammad
%A Wewer, Christopher
%A Wimmer, Thomas
%A Schiele, Bernt
%A Lenssen, Jan Eric
%+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
%T MEt3R: Measuring Multi-View Consistency in Generated Images : 
%G eng
%U http://hdl.handle.net/21.11116/0000-0010-7934-C
%R 10.1109/CVPR52734.2025.00566
%D 2025
%B IEEE/CVF Conference on Computer Vision and Pattern Recognition
%Z date of event: 2025-06-11 - 2025-06-15
%C Nashville, TN, USA
%B IEEE/CVF Conference on Computer Vision and Pattern Recognition
%P 6034 - 6044
%I IEEE
%@ 979-8-3315-4364-8

Conference paper

B. Pogodzinski, C. Wewer, B. Schiele, and J. E. Lenssen

“Spatial Reasoners for Continuous Variables in Any Domain,” in Proceedings of the ICML 2025 Workshop on Championing Open- source Development in Machine Learning (CODEML 2025), Vancouver, Canada, 2025.

@inproceedings{Pogodzinski_CODEML25,
TITLE = {Spatial Reasoners for Continuous Variables in Any Domain},
AUTHOR = {Pogodzinski, Bart and Wewer, Christopher and Schiele, Bernt and Lenssen, Jan Eric},
LANGUAGE = {eng},
URL = {https://openreview.net/forum?id=89GglVwjuK},
YEAR = {2025},
MARGINALMARK = {$\bullet$},
BOOKTITLE = {Proceedings of the ICML 2025 Workshop on Championing Open- source Development in Machine Learning (CODEML 2025)},
ADDRESS = {Vancouver, Canada},
}

Endnote

%0 Conference Proceedings
%A Pogodzinski, Bart
%A Wewer, Christopher
%A Schiele, Bernt
%A Lenssen, Jan Eric
%+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
%T Spatial Reasoners for Continuous Variables in Any Domain : 
%G eng
%U http://hdl.handle.net/21.11116/0000-0011-9116-0
%U https://openreview.net/forum?id=89GglVwjuK
%D 2025
%B Championing Open-source DEvelopment in ML Workshop @ ICML25
%Z date of event: 2025-07-19 - 2025-07-19
%C Vancouver, Canada
%B Proceedings of the ICML 2025 Workshop on Championing Open-
source Development in Machine Learning

Paper

C. Wewer, B. Pogodzinski, B. Schiele, and J. E. Lenssen

“Spatial Reasoning with Denoising Models,” 2025. [Online]. Available: https://www.arxiv.org/abs/2502.21075.

Abstract

We introduce Spatial Reasoning Models (SRMs), a framework to perform
reasoning over sets of continuous variables via denoising generative models.
SRMs infer continuous representations on a set of unobserved variables, given
observations on observed variables. Current generative models on spatial
domains, such as diffusion and flow matching models, often collapse to
hallucination in case of complex distributions. To measure this, we introduce a
set of benchmark tasks that test the quality of complex reasoning in generative
models and can quantify hallucination. The SRM framework allows to report key
findings about importance of sequentialization in generation, the associated
order, as well as the sampling strategies during training. It demonstrates, for
the first time, that order of generation can successfully be predicted by the
denoising network itself. Using these findings, we can increase the accuracy of
specific reasoning tasks from 1% to >50%.

BibTeX

@online{Wewer2502.21075,
TITLE = {Spatial Reasoning with Denoising Models},
AUTHOR = {Wewer, Christopher and Pogodzinski, Bart and Schiele, Bernt and Lenssen, Jan Eric},
LANGUAGE = {eng},
URL = {https://www.arxiv.org/abs/2502.21075},
EPRINT = {2502.21075},
EPRINTTYPE = {arXiv},
YEAR = {2025},
MARGINALMARK = {$\bullet$},
ABSTRACT = {We introduce Spatial Reasoning Models (SRMs), a framework to perform<br>reasoning over sets of continuous variables via denoising generative models.<br>SRMs infer continuous representations on a set of unobserved variables, given<br>observations on observed variables. Current generative models on spatial<br>domains, such as diffusion and flow matching models, often collapse to<br>hallucination in case of complex distributions. To measure this, we introduce a<br>set of benchmark tasks that test the quality of complex reasoning in generative<br>models and can quantify hallucination. The SRM framework allows to report key<br>findings about importance of sequentialization in generation, the associated<br>order, as well as the sampling strategies during training. It demonstrates, for<br>the first time, that order of generation can successfully be predicted by the<br>denoising network itself. Using these findings, we can increase the accuracy of<br>specific reasoning tasks from <1% to >50%.<br>},
}

Endnote

%0 Report
%A Wewer, Christopher
%A Pogodzinski, Bart
%A Schiele, Bernt
%A Lenssen, Jan Eric
%+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
%T Spatial Reasoning with Denoising Models : 
%G eng
%U http://hdl.handle.net/21.11116/0000-0010-DADB-2
%U https://www.arxiv.org/abs/2502.21075
%D 2025
%X   We introduce Spatial Reasoning Models (SRMs), a framework to perform<br>reasoning over sets of continuous variables via denoising generative models.<br>SRMs infer continuous representations on a set of unobserved variables, given<br>observations on observed variables. Current generative models on spatial<br>domains, such as diffusion and flow matching models, often collapse to<br>hallucination in case of complex distributions. To measure this, we introduce a<br>set of benchmark tasks that test the quality of complex reasoning in generative<br>models and can quantify hallucination. The SRM framework allows to report key<br>findings about importance of sequentialization in generation, the associated<br>order, as well as the sampling strategies during training. It demonstrates, for<br>the first time, that order of generation can successfully be predicted by the<br>denoising network itself. Using these findings, we can increase the accuracy of<br>specific reasoning tasks from <1% to >50%.<br>
%K Computer Science, Computer Vision and Pattern Recognition, cs.CV,Computer Science, Learning, cs.LG

2024

Conference paper

C. Wewer, K. Raj, E. Ilg, B. Schiele, and J. E. Lenssen

“latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction,” in Computer Vision -- ECCV 2024, Milano, Italy, 2024.

@inproceedings{WewerECCV24,
TITLE = {{latentSplat}: {A}utoencoding Variational {G}aussians for Fast Generalizable {3D} Reconstruction},
AUTHOR = {Wewer, Christopher and Raj, Kevin and Ilg, Eddy and Schiele, Bernt and Lenssen, Jan Eric},
LANGUAGE = {eng},
ISBN = {978-3-031-73020-7},
DOI = {10.1007/978-3-031-73021-4_27},
PUBLISHER = {Springer},
YEAR = {2024},
MARGINALMARK = {$\bullet$},
DATE = {2024},
BOOKTITLE = {Computer Vision -- ECCV 2024},
EDITOR = {Leonardis, Ale{\v s} and Ricci, Elisa and Roth, Stefan and Russakovsky, Olga and Sattler, Torsten and Varol, G{\"u}l},
PAGES = {456--473},
SERIES = {Lecture Notes in Computer Science},
VOLUME = {15145},
ADDRESS = {Milano, Italy},
}

Endnote

%0 Conference Proceedings
%A Wewer, Christopher
%A Raj, Kevin
%A Ilg, Eddy
%A Schiele, Bernt
%A Lenssen, Jan Eric
%+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
External Organizations
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
%T latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction : 
%G eng
%U http://hdl.handle.net/21.11116/0000-000F-D86F-2
%R 10.1007/978-3-031-73021-4_27
%D 2024
%B 18th European Conference on Computer Vision 
%Z date of event: 2024-09-29 - 2024-10-04
%C Milano, Italy
%B Computer Vision -- ECCV 2024
%E Leonardis, Ale&#353;; Ricci, Elisa; Roth, Stefan; Russakovsky, Olga; Sattler, Torsten; Varol, G&#252;l
%P 456 - 473
%I Springer
%@ 978-3-031-73020-7
%B Lecture Notes in Computer Science
%N 15145

Conference paper

S. Paul, C. Wewer, B. Schiele, and J. E. Lenssen

“Sp2360: Sparse-view 360° Scene Reconstruction using Cascaded 2D Diffusion Priors,” in ECCV 2024 Workshop on Wild 3D (ECCV 2024 Wild3D), Milan, Italy, 2024.

@inproceedings{Paul_Wild3D,
TITLE = {Sp2360: {S}parse-view 360$^{\circ}$ Scene Reconstruction using Cascaded {2D} Diffusion Priors},
AUTHOR = {Paul, Soumava and Wewer, Christopher and Schiele, Bernt and Lenssen, Jan Eric},
LANGUAGE = {eng},
URL = {https://openreview.net/forum?id=XuNhNyHHwK},
PUBLISHER = {OpenReview.net},
YEAR = {2024},
MARGINALMARK = {$\bullet$},
BOOKTITLE = {ECCV 2024 Workshop on Wild 3D (ECCV 2024 Wild3D)},
ADDRESS = {Milan, Italy},
}

Endnote

%0 Conference Proceedings
%A Paul, Soumava
%A Wewer, Christopher
%A Schiele, Bernt
%A Lenssen, Jan Eric
%+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
%T Sp2360: Sparse-view 360&#176; Scene Reconstruction using Cascaded 2D Diffusion Priors : 
%G eng
%U http://hdl.handle.net/21.11116/0000-0010-1041-2
%U https://openreview.net/forum?id=XuNhNyHHwK
%D 2024
%8 09.09.2024
%B ECCV 2024 Workshop on Wild 3D
%Z date of event: 2024-09-30 - 2024-09-30
%C Milan, Italy
%B ECCV 2024 Workshop on Wild 3D

%I OpenReview.net

2023

Conference paper

C. Wewer, E. Ilg, B. Schiele, and J. E. Lenssen

“SimNP: Learning Self-Similarity Priors Between Neural Points,” in IEEE/CVF International Conference on Computer Vision (ICCV 2023), Paris, France, 2023.

@inproceedings{Wewer_ICCV23,
TITLE = {{SimNP}: {L}earning Self-Similarity Priors Between Neural Points},
AUTHOR = {Wewer, Christopher and Ilg, Eddy and Schiele, Bernt and Lenssen, Jan Eric},
LANGUAGE = {eng},
ISBN = {979-8-3503-0718-4},
DOI = {10.1109/ICCV51070.2023.00812},
PUBLISHER = {IEEE},
YEAR = {2023},
MARGINALMARK = {$\bullet$},
DATE = {2023},
BOOKTITLE = {IEEE/CVF International Conference on Computer Vision (ICCV 2023)},
PAGES = {8807--8818},
ADDRESS = {Paris, France},
}

Endnote

%0 Conference Proceedings
%A Wewer, Christopher
%A Ilg, Eddy
%A Schiele, Bernt
%A Lenssen, Jan Eric
%+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
External Organizations
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
%T SimNP: Learning Self-Similarity Priors Between Neural Points : 
%G eng
%U http://hdl.handle.net/21.11116/0000-000D-C95E-8
%R 10.1109/ICCV51070.2023.00812
%D 2023
%B IEEE/CVF International Conference on Computer Vision
%Z date of event: 2023-10-02 - 2023-10-06
%C Paris, France
%B IEEE/CVF International Conference on Computer Vision
%P 8807 - 8818
%I IEEE
%@ 979-8-3503-0718-4