Friedrich-Alexander-Universität Erlangen-Nürnberg

Chair of Visual Computing
Cognitive Computer Vision Lab


This email address is being protected from spambots. You need JavaScript enabled to view it.

 

I study how humans and machines can perceive faces and shapes in general. In particular, I choose to focus on statistical shape models and the 3D Morphable Models as generative representation since they naturally disentangle the underlying variables. In combination with computer graphics we simulate the image formation process and approach the inverse problem in an analysis-by-synthesis manner. I'm junior professor (adidas Stiftungsprofessur) at the chair of visual computing at Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU). Before joing FAU I was a postdoc in Josh Tenenbaum's Computational Cognitive Science Lab at the Departement of Brain and Cognitive Sciences at MIT and the Center for Brains, Minds and Machines (CBMM) and Polina Golland's group at MIT Computer Science & Artificial Intelligence Lab. I did my PhD on facial image annotation and interpretation in unconstrained images in the Graphics and Vision Research Group at the University of Basel. Before my doctorate I obtained my M.Sc. and B.Sc. in Computer Science at the University of Basel and an upper secondary school teaching Diploma at the University of Applied Sciences Northwestern Switzerland.

Cognitive Computer Vision Lab (CogCoVi) - Doctoral Students

   
Valentin Bräutigam Andreea Dogaru Shreya Kapoor Maximilian Weiherer

AI-Experiment

   
KI/8
12.10.23
stacheliger Kaktus – Replik
100 x 100 cm
Acryl auf Leinwand
KI/7
11.10.23
KI 4
100 x 100 cm
KI und Acryl auf Leinwand

Here you can find all information to our AI-Art Project: AI-Experiment:
https://www.ki-experiment.tf.fau.de/

 

Publications

Generalizable 3D Scene Reconstruction via Divide and Conquer from a Single View [pdf] [project page] [code]
Andreea Dogaru, Mert Özer, Bernhard Egger
arXiv 2024

 

Exploring Multi-modal Neural Scene Representations With Applications on Thermal Imaging [pdf] [project page] [data]
Mert Özer*, Maximilian Weiherer*, Martin Hundhausen, Bernhard Egger
arXiv 2024

 

RANRAC: Robust Neural Scene Representations via Random Ray Consensus [pdf] [project page]
Benno Buschmann, Andreea Dogaru, Elmar Eisemann, Michael Weinmann, Bernhard Egger
arXiv 2024

 

TI2V-Zero: Zero-Shot Image Conditioning for Text-to-Video Diffusion Models [pdf] [project page]
Haomiao Ni, Bernhard Egger, Suhas Lohit, Anoop Cherian, Ye Wang, Toshiaki Koike-Akino, Sharon X Huang, Tim K Marks
Conference on Computer Vision and Pattern Recognition (CVPR), June 2024

 

exploreCOSMOS: Interactive Exploration of Conditional Statistical Shape Models in the Web-browser [pdf] [code] [web application]
Maximilian Hahn, Bernhard Egger
German Conference on Medical Image Computing Bildverarbeitung für die Medizin (BVM), 2024

 

GBOT: Graph-Based 3D Object Tracking for Augmented Reality-Assisted Assembly Guidance [pdf] [code] [data]
Shiyu Li, Hannah Schieber, Niklas Corell, Bernhard Egger, Julian Kreimeier, Daniel Roth
IEEE VR, Conference Virtual Reality and 3D User Interfaces 2024

 

 Approximating Intersections and Differences Between Linear Statistical Shape Models Using Markov Chain Monte Carlo [pdf]
Maximilian Weiherer, Finn Klein, Bernhard Egger
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024

 

ReWaRD: Retinal Waves for Pre-Training Artificial Neural Networks Mimicking Real Prenatal Development [pdf] [code] [data]
Benjamin Cappell, Andreas Stoll, Williams Chukwudi Umah, Bernhard Egger
Proceedings of the first edition of the Workshop on Unifying Representations in Neural Models (UniReps 2023) @ NeurIPS 2023

 

The Sky's the Limit: Re-lightable Outdoor Scenes via a Sky-pixel Constrained Illumination Prior and Outside-In Visibility [pdf] [code]
James A. D. Gardner, Evgenii Kashin, Bernhard Egger, William A. P. Smith
arXiv, 2023

 

RENI++ A Rotation-Equivariant, Scale-Invariant, Natural Illumination Prior [pdf] [code]
James A. D. Gardner, Bernhard Egger, William A. P. Smith
arXiv, 2023

 

ShaRPy: Shape Reconstruction and Hand Pose Estimation from RGB-D with Uncertainty [pdf]
Vanessa Wirth, Anna-Maria Liphardt, Birte Coppers, Johanna Bräunig, Simon Heinrich, Arnd Kleyer, Georg Schett, Martin Vossiek, Bernhard Egger, and Marc Stamminger
CVAMD Computer Vision for Automated Medical Diagnosis Workshop, IEEE/CVF International Conference on Computer Vision ICCV, 2023

 

Vschh 2023: A benchmark for the view synthesis challenge of human heads [pdf]
Youngkyoon Jang, Jiali Zheng, Jifei Song, Helisa Dhamo, Eduardo Pérez-Pellitero, Thomas Tanay, Matteo Maggioni, Richard Shaw, Sibi Catley-Chandar, Yiren Zhou, Jiankang Deng, Ruijie Zhu, Jiahao Chang, Ziyang Song, Jiahuan Yu, Tianzhu Zhang, Khanh-Binh Nguyen, Joon-Sung Yang, Andreea Dogaru, Bernhard Egger, Heng Yu, Aarush Gupta, Joel Julin, László A Jeni, Hyeseong Kim, Jungbin Cho, Dosik Hwang, Deukhee Lee, Doyeon Kim, Dongseong Seo, SeungJin Jeon, YoungDon Choi, Jun Seok Kang, Ahmet Cagatay Seker, Sang Chul Ahn, Ales Leonardis, Stefanos Zafeiriou
To NeRF or not to NeRF Workshop, IEEE/CVF International Conference on Computer Vision ICCV, 2023

 

PoseBias: On Dataset Bias and Task Difficulty-Is There an Optimal Camera Position for Facial Image Analysis? [pdf]
Mohit Choithwani, Sneha Almeida, Bernhard Egger
Analysis and Modeling of Faces and Gestures Workshop, IEEE/CVF International Conference on Computer Vision ICCV, 2023

 

BOSS: Bones, Organs and Skin Shape Model [pdf]
Karthik Shetty, Annette Birkhold, Srikrishna Jaganathan, Norbert Strobel, Bernhard Egger, Markus Kowarschik, Andreas Maier
Computers in Biology and Medicine, 2023

 

Building 3D Generative Models from Minimal Data [pdf]
Skylar Sutherland, Bernhard Egger, Joshua Tenenbaum
International Journal of Computer Vision (IJCV), 2023

 

PLIKS: A Pseudo-Linear Inverse Kinematic Solver for 3D Human Body Estimation [pdf]
Karthik Shetty, Annette Birkhold, Srikrishna Jaganathan, Norbert Strobel, Markus Kowarschik, Andreas Maier and Bernhard Egger
Conference on Computer Vision and Pattern Recognition (CVPR), June 2023
presented as highlight

 

To fit or not to fit: Model-based Face Reconstruction and Occlusion Segmentation from Weak Supervision [pdf] [code]
Chunlu Li, Andreas Morel-Forster, Thomas Vetter, Bernhard Egger*, Adam Kortylewski*
Conference on Computer Vision and Pattern Recognition (CVPR), June 2023

 

HOOREX: Higher Order Optimizers for 3D Recovery from X-Ray Images [pdf]
Karthik Shetty, Annette Birkhold, Bernhard Egger, Srikrishna Jaganathan, Norbert Strobel, Markus Kowarschik, Andreas Maier
ML4MHD Workshop on Machine Learning for Multimodal Healthcare Data, ICML 2023

 

Exploring the Capabilities of a Language Model-Only Approach for Depression Detection in Text Data [pdf]
Misha Sadeghi, Bernhard Egger, Reza Agahi, Robert Richer, Klara Capito, Lydia Helene Rupp, Lena Schindler-Gmelch, Matthias Berking, Bjoern M Eskofier
IEEE EMBS International Conference on Biomedical and Health Informatics (BHI), 2023

 

Survey and Systematization of 3D Object Detection Models and Methods [pdf]
Moritz Drobnitzky, Jonas Friederich, Bernhard Egger, Patrick Zschech
The Visual Computer, 2023

 

State of the Art in Dense Monocular Non-Rigid 3D Reconstruction [pdf]
Edith Tretschk, Navami Kairanda, Mallikarjun B R, Rishabh Dabral, Adam Kortylewski, Bernhard Egger, Marc Habermann, Pascal Fua, Christian Theobalt, Vladislav Golyanik
EUROGRAPHICS State-of-the-Art Report (STARs), 2023
DOI: http://dx.doi.org/10.1111/cgf.14774

 

Evaluating 3D human face reconstruction from a frontal 2D image, focusing on facial regions associated with foetal alcohol syndrome [pdf] [press]
Felix Atuhaire, Bernhard Egger, Tinashe Mutsvangwa
South African Journal of Science, 2023
DOI: https://doi.org/10.17159/sajs.2023/12064

 

NeRFtrinsic Four: An End-To-End Trainable NeRF Jointly Optimizing Diverse Intrinsic and Extrinsic Camera Parameters [pdf]
Hannah Schieber, Fabian Deuser, Bernhard Egger, Norbert Oswald, Daniel Roth
arXiv, 2023

 

Rotation-Equivariant Conditional Spherical Neural Fields for Learning a Natural Illumination Prior [pdf] [project page] [code] [data]
James AD Gardner, Bernhard Egger, William AP Smith
NeurIPS, 2022

 

A Lightweight Machine Learning Pipeline for LiDAR-simulation [pdf]
Richard Marcus, Niklas Knoop, Bernhard Egger and Marc Stamminger
In Proceedings of the 3rd International Conference on Deep Learning Theory and Applications - DeLTA, 176-183, Lisbon, Portugal, 2022
DOI: https://doi.org/10.5220/0011309100003277

 

MOST-GAN: 3D Morphable StyleGAN for Disentangled Face Image Manipulation [pdf] [video]
Safa C. Medin, Bernhard Egger, Anoop Cherian, Ye Wang, Joshua B. Tenenbaum, Xiaoming Liu, Tim K. Marks
36th AAAI Conference on Artificial Intelligence 2022
DOI: https://doi.org/10.1609/aaai.v36i2.20091

 

Learning the shape of female breasts: an open-access 3D statistical shape model of the female breast built from 110 breast scans [pdf]
Maximilian Weiherer, Andreas Eigenberger, Bernhard Egger, Vanessa Brébant, Lukas Prantl, Christoph Palm
The Visual Computer, 2022
DOI: https://doi.org/10.1007/s00371-022-02431-3

 

Identity-Expression Ambiguity in 3D Morphable Face Models [pdf] [video]
Bernhard Egger, Skylar Sutherland, Safa C. Medin, Josh Tenenbaum
Conference on Automatic Face and Gesture Recognition, December 2021
Round 1 accept, oral presentation, best poster award

 

Beyond Flatland: Pre-training with a Strong 3D Inductive Bias [pdf] [talk]
Shubhaankar Gupta, Thomas P O'Connell, Bernhard Egger
Preregistration Workshop at NeurIPS'21.

 

Improving the reconstruction of disentangled representation learners via multi-stage modelling [pdf]
Akash Srivastava, Yamini Bansal, Yukun Ding, Cole Hurwitz, Kai Xu, Bernhard Egger, Prasanna Sattigeri, Josh Tenenbaum, David D Cox, Dan Gutfreund
arXiv, 2021

 

Building 3D Morphable Models from a Single Scan [pdf] [code]
Skylar Sutherland, Bernhard Egger, Josh Tenenbaum
International Conference on Computer Vision (ICCV) Workshops, October 2021

 

Seeing in the dark: Testing deep neural network and analysis-by-synthesis accounts of 3D shape perception with highly degraded images [pdf]
Hakan Yilmaz, Gargi Singh, Bernhard Egger, Joshua B Tenenbaum, Ilker Yildirim
43nd Annual Virtual Meeting of the Cognitive Science Society (CogSci), July 2021

 

Deep Learning compatible Differentiable X-ray Projections for Inverse Rendering [pdf]
Karthik Shetty, Annette Birkhold, Norbert Strobel, Bernhard Egger, Srikrishna Jaganathan, Markus Kowarschik, Andreas Maier
Bildverarbeitung für die Medizin (BVM) 2021

 

What computational model provides the best explanation of face representations in the primate brain? [pdf]
Le Chang, Bernhard Egger, Thomas Vetter, Doris Y. Tsao
Current Biology,  2021
DOI: https://doi.org/10.1101/2020.06.07.111930

 

Inverse Rendering Best Explains Face Perception Under Extreme Illuminations
Bernhard Egger, Max Siegel, Riya Arora, Amir Arsalan Soltani, Ilker Yildirim, Josh Tenenbaum
42nd Annual Virtual Meeting of the Cognitive Science Society (CogSci), July 2020

 

A Morphable Face Albedo Model [pdf] [code] [model]
William A.P Smith, Alassane Seck, Hannah Dee, Bernard Tiddeman, Josh Tenenbaum, Bernhard Egger
Conference on Computer Vision and Pattern Recognition (CVPR), June 2020
oral presentation
https://openaccess.thecvf.com/content_CVPR_2020/papers/Smith_A_Morphable_Face_Albedo_Model_CVPR_2020_paper.pdf

 

3D Morphable Face Models - Past, Present and Future [pdf] [video]
Bernhard Egger, William A.P Smith, Ayush Tewari, Stefanie Wuhrer, Michael Zollhoefer, Thabo Beeler, Florian Bernard, Timo Bolkart, Adam Kortylewski, Sami Romdhani, Christian Theobalt, Volker Blanz, Thomas Vetter
ACM Transactions on Graphics, 2020
DOI: https://doi.org/10.1145/3395208

 

3D Morphable Models (Dagstuhl Seminar 19102) [pdf]
Editors: Bernhard Egger and William Smith and Christian Theobalt and Thomas Vetter
Dagstuhl Reports, Schloss Dagstuhl-Leibniz-Zentrum fuer Informatik, Dagstuhl, Germany, 2019
DOI: http://doi.org/10.4230/DagRep.9.3.16

 

Patient-specific Conditional Joint Models of Shape, Image Features and Clinical Indicators [pdf] [video]
Bernhard Egger, Markus Schirmer, Florian Dubost, Marco Nardin, Natalia Rost, Polina Golland
International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) 2019, Shenzhen, China, October 2019
Early Accept
DOI: https://doi.org/10.1007/978-3-030-32251-9_11

 

Analyzing and Reducing the Damage of Dataset Bias to Face Recognition with Synthetic Data [pdf] [code]
Adam Kortylewski, Bernhard Egger, Andreas Schneider, Thomas Gerig, Andreas Morel-Forster, Thomas Vetter
Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, June 2019
Best Paper Award
https://openaccess.thecvf.com/.../Kortylewski_Analyzing_and_Reducing_the_Damage_of_Dataset_Bias_to_Face_CVPRW_2019_paper.pdf

 

Shape in Medical Imaging [webpage]
Editors: Martin Reuter, Christian Wachinger, Hervé Lombaert, Beatriz Paniagua, Marcel Lüthi, Bernhard Egger
International Workshop, ShapeMI 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 20, 2018, Proceedings
DOI: https://doi.org/10.1007/978-3-030-04747-4

 

Occlusion-aware 3D Morphable Models and an Illumination Prior for Face Image Analysis [pdf] [tutorial] [code]
Bernhard Egger, Sandro Schönborn, Andreas Schneider, Adam Kortylewski, Andreas Morel-Forster, Clemens Blumer and Thomas Vetter
International Journal of Computer Vision (IJCV), 2018
DOI: https://doi.org/10.1007/s11263-018-1064-8

 

Empirically Analyzing the Effect of Dataset Biases on Deep Face Recognition Systems [pdf] [code]
Adam Kortylewski, Bernhard Egger, Andreas Schneider, Thomas Gerig, Andreas Morel-Forster, Thomas Vetter
Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, June 2018
http://openaccess.thecvf.com/content_cvpr_2018_workshops/papers/w41/Kortylewski_Empirically_Analyzing_the_CVPR_2018_paper.pdf

 

Morphable Face Models - An Open Framework [pdf] [code]
Thomas Gerig, Andreas Morel-Forster, Clemens Blumer, Bernhard Egger, Marcel Lüthi, Sandro Schönborn, Thomas Vetter
Conference on Automatic Face and Gesture Recognition, May 2018
DOI: https://doi.org/10.1109/FG.2018.00021

 

A Parametric Freckle Model for Faces [pdf]
Andreas Schneider, Bernhard Egger, Thomas Vetter
Conference on Automatic Face and Gesture Recognition, May 2018
DOI: https://doi.org/10.1109/FG.2018.00069

 

Efficient Global Illumination for Morphable Models [pdf] [tutorial]
Andreas Schneider, Sandro Schönborn, Bernhard Egger, Lavrenti Frobeen, Thomas Vetter
International Conference on Computer Vision (ICCV), October 2017
DOI: https://doi.org/10.1109/ICCV.2017.417

 

Copula Eigenfaces with Attributes: Semiparametric Principal Component Analysis for a Combined Color, Shape and Attribute Model [pdf
Bernhard Egger*, Dinu Kaufmann*, Sandro Schönborn, Volker Roth and Thomas Vetter
Communications in Computer and Information Science book series (CCIS, volume 693), 2017
DOI: https://doi.org/10.1007/978-3-319-64870-5_5

 

Semantic Morphable Models [pdf] [code]
Bernhard Egger
PhD Thesis, University of Basel, 2017
DOI: https://doi.org/10.5451/unibas-006722192

 

Probabilistic Morphable Models [pdf] [code]
Bernhard Egger, Sandro Schönborn, Clemens Blumer, Thomas Vetter
Bookchapter in: Statistical Shape and Deformation Analysis - Methods, Implementation and Applications, Elsevier 2017
DOI: https://doi.org/10.1016/B978-0-12-810493-4.00006-7

 

Markov Chain Monte Carlo for Automated Face Image Analysis [pdf] [tutorial] [code]
Sandro Schönborn, Bernhard Egger, Andreas Morel-Forster, Thomas Vetter
International Journal of Computer Vision (IJCV), 2017
DOI: http://dx.doi.org/10.1007/s11263-016-0967-5  

 

Occlusion-aware 3D Morphable Face Models [data] [pdf] [press] [code]
Bernhard Egger, Andreas Schneider, Clemens Blumer, Andreas Morel-Forster, Sandro Schönborn, Thomas Vetter
British Machine Vision Conference (BMVC), September 2016
DOI: https://dx.doi.org/10.5244/C.30.64

 

Copula Eigenfaces - Semiparametric Principal Component Analysis for Facial Appearance Modeling [pdf
Bernhard Egger*, Dinu Kaufmann*, Sandro Schönborn, Volker Roth and Thomas Vetter
11th International Conference on Computer Graphics Theory and Applications (GRAPP), February 27-29, 2016 
DOI:  http://dx.doi.org/10.5220/0005718800480056

 

Background Modeling for Generative Image Models [pdf] [code]
Sandro Schönborn, Bernhard Egger, Andreas Forster, and Thomas Vetter
Computer Vision and Image Understanding (CVIU), 2015
DOI: http://dx.doi.org/10.1016/j.cviu.2015.01.008 

 

Pose Normalization for Eye Gaze Estimation and Facial Attribute Description from Still Images [pdf
Bernhard Egger, Sandro Schönborn, Andreas Forster and Thomas Vetter
IN: 36th German Conference of Pattern Recognition, GCPR 2014,
Münster, Germany, September 2-5, 2014
DOI: http://dx.doi.org/10.1007/978-3-319-11752-2_25 

 

A Monte Carlo Strategy to Integrate Detection and Model-Based Face Analysis [pdf] [code]
Sandro Schönborn, Andreas Forster, Bernhard Egger and Thomas Vetter
IN: 35th German Conference of Pattern Recognition, GCPR 2013,
Saarbrücken, Germany, September 3-6, 2013
DOI: http://dx.doi.org/10.1007/978-3-642-40602-7_11 

Videos

Identity-Expression Ambiguity in 3D Morphable Face Models - AFC Lab Talk Series

Identity-Expression Ambiguity in 3D Morphable Face Models 

3D Morphable Face Models - Past, Present and Future - Presentation - SIGGRAPH oral

A Morphabe Face Albedo Model

Patient-specific Conditional Joint Models of Shape, Image Features and Clinical Indicators

My presentation at the IPAM Workshop I: Geometric Processing

Varia

Curated List of 3D Morphable Model Software and Data [list]
one result from Dagstuhl seminar on 3D Morphable Models in March 2019

 

Semantic Morphable Model Tutorial [resources]
Bernhard Egger and Thomas Vetter

 

Probabilistic Fitting Tutorial [resources]
Sandro Schönborn, Andreas Morel-Forster, Bernhard Egger and Thomas Vetter

 

Teaching Shape Modelling at High Schools [resources]
Bernhard Egger, Sandro Schönborn and Thomas Vetter
IN: Proceedings of the 2nd Shape Symposium, 2015, Delémont, Switzerland, September 30 - October 2, p 19.
Proceedings: http://shapesymposium.org

SIGBOVIK

AMOR: Ambiguous Authorship Order [pdf]
Maximilian Weiherer, Andreea Dogaru, Shreya Kapoor, Hannah Schieber, Bernhard Egger
SIGBOVIK (Special Interest Group on Harry Quechua Bovik),  April 5th 2024

 

From Zero to Hero: Convincing with Extremely Complicated Math [pdf]
Maximilian Weiherer and Bernhard Egger
SIGBOVIK (Special Interest Group on Harry Quechua Bovik),  March 31st 2023

 

A Free Computer Vision Lesson for Car Manufacturers or It is Time to Retire the Erlkonig [pdf]
Maximilian Weiherer and Bernhard Egger
SIGBOVIK (Special Interest Group on Harry Quechua Bovik), April 8st 2022

 

ACTION: A Catchy Title Is all yOu Need! [pdf]
Bernhard Egger, Kevin Smith*, Thomas O’Connell*, Max Siegel (*Co-middle Authors)
SIGBOVIK (Special Interest Group on Harry Quechua Bovik), April 8st 2022

 

(Un)helper functions [pdf]
Kevin Smith and Bernhard Egger
SIGBOVIK (Special Interest Group on Harry Quechua Bovik), April 8st 2022

 

openCHEAT: Computationally Helped Error bar Approximation Tool-Kickstarting Science 4.0 [pdf]
Bernhard Egger, Kevin Smith, David Cox, Max Siegel (Co-First and Co-Last Authors)
SIGBOVIK (Special Interest Group on Harry Quechua Bovik), April 1st 2021

 

HonkFast, PreHonk, HonkBack, PreHonkBack, HERS, AdHonk and AHC: the Missing Keys for Autonomous Driving [pdf]
Bernhard Egger, Max Siegel (Co-First and Co-Last Authors)
SIGBOVIK (Special Interest Group on Harry Quechua Bovik), April 1st 2020
Honk award

 

These authors contributed equally to this work