Michael Neumayr

PhD in Computer Science @ UofT

prof_pic.png

I am a PhD student in Computer Science at the University of Toronto, working on 3D computer vision and generative models under the supervision of David Lindell. I graduated with an M.Sc. in Computer Science from TU Munich.

My M.Sc. thesis was at the University of Toronto with Sherwin Bahmani and David Lindell. I worked as a research assistant at the Ommerlab with Stephan Baumann. My Master’s courses included a project on generalizable novel view synthesis with David Rozenberszki and research on diffusion models in medical imaging with Cosmin Bercea and Julia Schnabel.

I obtained a B.Sc. in Computer Science and B.A. in Philosophy from the University of Munich.

Publications

  1. attribute.png
    Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions
    Stefan Andreas Baumann, Felix Krause, Michael Neumayr, and 4 more authors
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025
    DOI arXiv PDF Code Website
  2. autoddpm.gif
    Mask, Stitch, and Re-Sample: Enhancing Robustness and Generalizability in Anomaly Detection through Automatic Diffusion Models
    Cosmin I Bercea*, Michael Neumayr*, Daniel Rueckert, and 1 more author
    In ICML 3rd Workshop on Interpretable Machine Learning in Healthcare (IMLH), 2023
    arXiv HTML PDF Code Website
  3. dipencoder.png
    The Dipencoder: Enforcing multimodality in autoencoders
    Collin Leiber, Lena GM Bauer, Michael Neumayr, and 2 more authors
    In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2022
    DOI HTML PDF Code Slides

Teaching Assistant

At University of Toronto:
At Technical University of Munich:
  • CIT4230003: Advanced Machine Learning: Deep Generative Models - Summer 2025
  • CIT4230003: Advanced Machine Learning: Deep Generative Models - Summer 2024
At University of Munich:
  • Introduction to Computer Science: Systems and Applications - Summer 2021

Projects

project thumbnail
Novel View Synthesis for Scenes in the Wild

Advanced Deep Learning for Visual Computing by Prof. Nießner
project thumbnail
Restauration-based Anomaly Detection with AutoDDPM

Guided Research supervised by Cosmin I. Bercea

News

Sep 01, 2025 I joined the lab of David Lindell at the University of Toronto as a PhD student in Computer Science.
Aug 31, 2025 I finished my Master of Science in Computer Science at TU Munich.
Jun 11, 2025 I attended CVPR 2025 in Nashville from June 11, 2025 - June 15, 2025.