Machine learning · Computer vision

DominikNarnhofer_

I’m a researcher at ETH Zurich, working on computer vision and machine learning in the PRS group led by Prof. Konrad Schindler. My research interests include generative models, 3D computer vision, and fundamental machine learning.

I received my PhD from TU Graz in 2023 under the supervision of Prof. Thomas Pock with the thesis, Generative Models and Uncertainty for Inverse Problems in Imaging.

Email me ↗Google Scholar ↗ORCID ↗

                                                                                    
                                                                                    
                                       .;**;.                                       
                                      .:%@@#,.                                      
                               .,.,,,:;,;==:,;:,,...,                               
                            ...,;;...,=+;=;=*;....;;,...                            
                         ,=;.::..*;.,,.+#:;%;.,,.==..;,,;;,                         
                       .,#@@*,+.,#:.:,.:@=+@,.,:.;#..*,#@@#..                       
                     ...:;++:==:*;.,.,.,*;;*..,...;*,+;:++;,..                      
                    .,..,,,:;**#;,..,.,+;+==+..,.,:=#++::,,..,,.                    
                   .,=:...,.;#*;:;+:.,*+====++..;+;:;*#;.,...;=,.                   
                  .:;;+....+*,....,*:+=:.::.:++;*.....:*=....*;;,.                  
                 .,;;:*=.,+=.......,%+;..=;..;*#........=+..++::;,                  
                 .;,.,,#,;::;;;;:,,.*=;,....:;*+.,,:;;;;,;;:*,,.::.                 
                 .;:...;;,;+++**++=;,*=;,..:;=+,;=++**+++;,;:...;:.                 
                  .;...:::;++*###%%%+:+=======:+%%%###*+=;:::..,;.                  
                 .:,:,%%+:;=+*###%%##*,=;#*;=:###%%###*+;::*@#,:,:.                 
                 .:.,:==;;;=*###@@##*#;:==;=,=#*##@%###*;;:;+=:..:.                 
                .,:..,.,,;:;==+*##*****:;..;;*****##*+==;::,,.,..:.                 
               .,;*=..;:,;;===;:,,::;+**;::;**=;:::::;===;:,:;..++:..               
              .,;;=%=.=.,,,:;::=;:,,,,:+*++#+,.,,::=;::::,,.,;.*#;;;,.              
              ,%@+;=#,:,;......;....,:,:#%%*:,:,...;.......:,,:#;;*@#:              
              ,+*=:;*...=+:::,.....,,+=,*@@+,++,,,...,,:::+;..,*::=*+,              
               .,,:=;....;+=;;;==++###+;*@@+;+###+==;;;;=+:..,.==:,,.               
                ,:=;..=.,+;;+=*##%@%##+;+@%+;+##%@%##+=+;==.,;..;;:.                
                 ,,,,.:=,=:.==**##%##+;=*@@*==*##%##*+=;.:;,=,.,,,.                 
                  .;;,.:;,..:=++*####;;;=##=;;=####*+==,..:;,.,=:.                  
                   .,..,.:;;,:+++****+;,....,;*##**+==:,;;,.,.,,.                   
                      .,,..,=;:=++**###*+;;+#####*++=:;=,..;,.                      
                       .;,...=::=++++=;:,::,:;=++++=:;;...::.                       
                        .:,..,;:==+==::;+;=+=::==+;=:;...::.                        
                          ,:,:::=;;+++;;::::;=+++;==::,::,                          
                            .,,:;=:+++**+**+**++=:=;,,,.                            
                            .,...,,==+=;#%%#;+++;,,.....                            
                            .:......,;:;++++;:;,.....::.                            
                           .:::.,,,...............,.,;::.                           
                          ,;..,;=;=,...,;::;....:;;=;,.,;.                          
                         .;...,:,:=*=.,+,:,:=.,++;:,,...,;.                         
                       :::...=%@*..,#+:=.:..=,#+..:%@#:..,:,                        
                       ,:=:..,=+;...,%=;:..=:**...,=+;..,;=,                        
                        .:;;:,.....,.+#,;==::#:.,....,:;;;,.                        
                         .,::;====;:.++,+@%;,*;.;=====;:,,.                         
                           .,:;=+***=+::=++;,;==***=;:,,.                           
                              .,:;=+=;:;=;;=::;==;;,,.                              
                                       .,,,..

NEUROMANCER / ASCII PORTRAITPIXELS → TEXT

01 News

Oct 2026

Upcoming talk in Prague

I will give a talk at the HarmonyOS Technology Innovation Summit in Prague in October 2026.

2026

Two papers accepted at NeurIPS 2026

Unified Panoramic Geometry Estimation via Multi-View Foundation Models ↗ and Stitched Value Model for Diffusion Alignment ↗ have been accepted at NeurIPS 2026.

Aug 2026

Round 2 ETHAR grant accepted

Our Round 2 ETHAR grant for “Spatial State Memory and Continuous Consistency for Fast Generative 3D Scene Evolution” has been accepted.

Mar 2026

MeanFlow paper accepted at CVPR 2026

Our paper Understanding, Accelerating, and Improving MeanFlow Training ↗ has been accepted at CVPR 2026.

Jan 2026

Two papers accepted at ICLR 2026

VIST3A: Text-to-3D by Stitching a Multi-View Reconstruction Network to a Video Generator ↗ and Continuous Space-Time Video Super-Resolution with 3D Fourier Fields ↗ have been accepted at ICLR 2026. VIST3A was selected for an oral presentation.

Aug 2025

ETHAR grant accepted

Our ETHAR grant for “Stochastic Interpolants for Controllable Scene Generation” has been accepted.

02 Research

My work explores generative models for visual reconstruction and synthesis, from images and video to three-dimensional scenes.

Generative Models3D Computer VisionFundamental Machine Learning

Publications & preprints

Google Scholar ↗

Journal and conference papers, preprints, workshops, and other research contributions. Preprint and published versions are listed together.

2026

CVPR 2026

Understanding, Accelerating, and Improving MeanFlow Training

Jin-Young Kim, Hyojun Go, Lea Bogensperger, Julius Erbach, Nikolai Kalischek, Federico Tombari, Konrad Schindler, Dominik Narnhofer

Understanding the dynamics of velocity learning to make few-step generative modeling faster and more effective.

Paper ↗

ICLR 2026 Oral

VIST3A: Text-to-3D by Stitching a Multi-View Reconstruction Network to a Video Generator

Hyojun Go, Dominik Narnhofer, Goutam Bhat, Prune Truong, Federico Tombari, Konrad Schindler

Connecting video generation and multi-view reconstruction to generate 3D representations directly from text.

Project ↗Paper ↗

ICLR 2026

Continuous Space-Time Video Super-Resolution with 3D Fourier Fields

Alexander Becker, Julius Erbach, Dominik Narnhofer, Konrad Schindler

Representing video as a continuous field to reconstruct spatial detail and motion at flexible resolutions and frame rates.

Project & code ↗

Preprint · 2026

Guided Super-Resolution of Digital Elevation Models with Diffusion-Based Image Generators

Armand Mihai Nicolicioiu, Dominik Narnhofer, Nando Metzger, Daniel Panangian, Ksenia Bittner, Konrad Schindler

Publication ↗

NeurIPS · 2026

Unified Panoramic Geometry Estimation via Multi-View Foundation Models

Vukasin Bozic, Isidora Slavkovic, Dominik Narnhofer, Nando Metzger, Denis Rozumny, Konrad Schindler, Nikolai Kalischek

Publication ↗

NeurIPS · 2026

Stitched Value Model for Diffusion Alignment

Hyojun Go, Hyungjin Chung, Prune Truong, Goutam Bhat, Li Mi, Zhaochong An, Zixiang Zhao, Dominik Narnhofer, Serge Belongie, Federico Tombari, Konrad Schindler

Publication ↗

Transactions on Machine Learning Research · 2026

LoRA-Ensemble: Efficient Uncertainty Modelling for Self-Attention Networks

Dominik J. Mühlematter, Michelle Halbheer, Alexander Becker, Dominik Narnhofer, Helge Aasen, Konrad Schindler, Mehmet Ozgur Turkoglu

Publication ↗

Preprint · 2026

Repurposing Protein Language Models for Latent Flow-Based Fitness Optimization

Amaru Caceres Arroyo, Lea Bogensperger, Ahmed Allam, Michael Krauthammer, Konrad Schindler, Dominik Narnhofer

Publication ↗

2025

NeurIPS · 2025

Solving Inverse Problems with FLAIR

Julius Erbach, Dominik Narnhofer, Andreas Dombos, Bernt Schiele, Jan Eric Lenssen, Konrad Schindler

Publication ↗

CVPR · 2025

Video Depth without Video Models

Bingxin Ke, Dominik Narnhofer, Shengyu Huang, Lei Ke, Torben Peters, Katerina Fragkiadaki, Anton Obukhov, Konrad Schindler

Publication ↗

ICML · 2025

A Variational Perspective on Generative Protein Fitness Optimization

Lea Bogensperger, Dominik Narnhofer, Ahmed Allam, Konrad Schindler, Michael Krauthammer

Publication ↗

International Journal of Computer Vision · 2025

FlowSDF: Flow Matching for Medical Image Segmentation Using Distance Transforms

Lea Bogensperger, Dominik Narnhofer, Alexander Falk, Konrad Schindler, Thomas Pock

Publication ↗

Transactions on Machine Learning Research · 2025

Thera: Aliasing-Free Arbitrary-Scale Super-Resolution with Neural Heat Fields

Alexander Becker, Rodrigo Caye Daudt, Dominik Narnhofer, Torben Peters, Nando Metzger, Jan Dirk Wegner, Konrad Schindler

Publication ↗

2024

CVPR · 2024

MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detection

Jakub Micorek, Horst Possegger, Dominik Narnhofer, Horst Bischof, Mateusz Kozinski

Publication ↗

SIAM Journal on Imaging Sciences · 2024

Posterior-Variance-Based Error Quantification for Inverse Problems in Imaging

Dominik Narnhofer, Andreas Habring, Martin Holler, Thomas Pock

Publication ↗

Book chapter · Springer INdAM Series · 2024

Majoration-Minimization for Sparse SVMs

Alessandro Benfenati, Emilie Chouzenoux, Giorgia Franchini, Salla Latva-Äijö, Dominik Narnhofer, Jean-Christophe Pesquet, Sebastian J. Scott, Mahsa Yousefi

Publication ↗

International Snow Science Workshop · 2024