Dominik Muhle

Ph.D. Candidate — 3D Scene Reconstruction, TU Munich
Munich, Germany dominikmuhle@icloud.com
Academics
Since 04/2022

Ph.D. · Technical University of Munich (TUM)

Munich, Germany

Ph.D. in 3D Scene Reconstruction at the Chair of Computer Vision & Artificial Intelligence in the Computer Vision Group under the supervision of Prof. Dr. Daniel Cremers.

10/2018 – 10/2021

M.Sc. Robotics, Cognition, Intelligence · TUM

Munich, Germany · Final Grade: 1.4

  • Master's Thesis: “Frame-To-Frame Rotation Estimation under Uncertain Feature Positions for Visual Odometry” (Grade: 1.0)
  • WS 19/20: Tutor for the course “Machine Learning”
10/2015 – 09/2018

B.Sc. Electrical Engineering · Karlsruhe Institute of Technology (KIT)

Karlsruhe, Germany · Final Grade: 1.3

Bachelor's Thesis: “Sensorlose Regelung einer permanenterregten Synchronmaschine”.

2007 – 2015

High School · Gymnasium Unterrieden

Sindelfingen, Germany · Final Grade: 1.3

Honors: DPG-Abiturpreis, DMV-Abiturpreis, Ferry Porsche Preis.

Professional Experience
10/2019 – 03/2021

Founding Member · WARP

Munich, Germany · Start-up for autonomous driving for sub-car vehicles

  • Supervision of student interns in the area of LiDAR Odometry and Mapping (LOAM)
  • Research and implementation of a custom SOTA feature-based Visual Odometry algorithm
05/2019 – 09/2019

Student Team · ROBOY

Munich, Germany · Humanoid Robotics Research Project

  • Implementation of a navigation stack for LiDAR Simultaneous Localization and Mapping
  • Implementation of longitudinal and lateral vehicle control using MYO-muscles
10/2016 – 01/2019

Co-founder · FlowerAI

Munich, Germany · Start-up for an intelligent gardening assistant

  • Financed and supported by UnternehmerTUM; participated in the Google Cloud Start-up Program with $20,000 in cloud credits
  • Development of autonomous irrigation hardware
  • Patent application for the automatic fertilizer dispenser
  • Moisture prediction using machine learning
03/2018 – 09/2018

Intern · Bosch

Schwieberdingen, Germany · Department: Power Train Solutions

  • Design of a control system that switches between low-speed and high-speed control
  • Implementation of the control system in MATLAB Simulink with a provided motor model
  • Validation of the control system with a real motor
Skills & Languages

Languages

GermanNative
EnglishC1 · Cambridge CAE
FrenchB1

Technical Skills

Python PyTorch Numpy C++ ROS/ROS2 LaTeX MATLAB Simulink Linux macOS Windows

very good good

Publications
EquiFusion: Kinematics-Agnostic Human Motion Prediction via Equivariant Latent Diffusions
C. Curreli, F. Hofherr, D. Muhle, A. Saroha, R. Marin, D. Cremers · ECCV 2026
VOCA: Visual Odometry with Codec Awareness
N. A. Hilscher, M. de Mayo, D. Muhle, C. Otten gennant Hermes, D. Cremers · ECCV 2026
C3PO: Canonicalization of 3D Pose from Partial Views with Generalizable Correspondence Features
Y. Chi, L. Sommer, O. Dünkel, D. Muhle, D. Cremers, C. Theobalt, A. Kortylewski · 3DV 2026
IPFormer: Visual 3D Panoptic Scene Completion with Context-Adaptive Instance Proposals
M. Gross, A. Fahmy, D. Niwattananan, D. Muhle, R. Song, R. Marin, D. Cremers, H. Meeß · NeurIPS 2025
Dream-to-Recon: Monocular 3D Reconstruction with Diffusion-Depth Distillation from Single Images
P. Wulff, F. Wimbauer, D. Muhle, D. Cremers · ICCV 2025
GECO: Geometrically Consistent Embedding with Lightspeed Inference
R. Hartwig, D. Muhle, R. Marin, D. Cremers · ICCV 2025
AnyCam: Learning to Recover Camera Poses and Intrinsics from Casual Videos
F. Wimbauer, W. Chen, D. Muhle, C. Rupprecht, D. Cremers · CVPR 2025
Nonisotropic Gaussian Diffusion for Realistic 3D Human Motion Prediction
C. Curreli, D. Muhle, A. Saroha, Z. Ye, R. Marin, D. Cremers · CVPR 2025
Ground-Aware Automotive Radar Odometry
D. Casado Herraez, F. Kaschner, M. Zeller, D. Muhle, J. Behley, M. Heidingsfeld, D. Cremers, C. Stachniss · ICRA 2025
Gaussian Splatting in Style
A. Saroha, M. Gladkova, C. Curreli, D. Muhle, T. Yenamandra, D. Cremers · GCPR 2024
Boosting Self-Supervision for Single-View Scene Completion via Knowledge Distillation
K. Han, D. Muhle, F. Wimbauer, D. Cremers · CVPR 2024
S4C: Self-Supervised Semantic Scene Completion with Neural Fields
A. Hayler, F. Wimbauer, D. Muhle, C. Rupprecht, D. Cremers · 3DV 2024, Spotlight
Learning Correspondence Uncertainty via Differentiable Nonlinear Least Squares
D. Muhle, L. Koestler, K. M. Jatavallabhula, D. Cremers · CVPR 2023
The Probabilistic Normal Epipolar Constraint for Frame-To-Frame Rotation Optimization under Uncertain Feature Positions
D. Muhle, L. Koestler, N. Demmel, F. Bernard, D. Cremers · CVPR 2022
Düngereinrichtung, Bewässerungssystem sowie Verfahren zum Betreiben eines Bewässerungssystems
F. Dinkelacker, D. Muhle, S. Muhle, M. Schlinger · Patent Nr. 10201714740
Selected Scholarships
11/2019 – 10/2020

Deutschlandstipendium · TUM

Financial scholarship for excellent students, financed in equal parts by the private sector and the state.

10/2019 – 10/2021

best.in.tum · TUM

Promotion of outstanding students at the Department of Informatics.

03/2017 – 10/2017

UnternehmerTUM [x]

Financial support for FlowerAI.

Others
2013 – 2015

Summer Camp Tutor · Eichholzer Täle

Sindelfingen, Germany

2013

Intel Leibniz Challenge

Participated with great success.