Leon Sick

Visual Computing Group. Ulm University

Leon.jpeg

Hi and welcome! I’m currently a Ph.D. student at Ulm University where I’m part of the Visual Computing Group. My main supervisor is Timo Ropinski, but I also work closely with Pedro Hermosilla. My research is mainly focused on self-supervised pre-training, unsupervised segmentation, and different applications of Vision Transformers. Currently, I’m working hard to fill my publications page!

Previously, I was a Ph.D. student at Liebherr. I also try to regularly write blog posts explaining papers to starters in the field of AI. If you are interested, feel free to stop by on Medium.

And when I’m not researching, you can either find me on a sail boat or fishing during summer, but also skiing in the winter.

news

Jan 21, 2025 Super excited that our work on attention-guided masked autoencoders was awarded an Oral presentation at WACV 2025! :tada:
Nov 5, 2024 I’m happy to be recognized as a top reviewer at NeurIPS 2024! My first time as a reviewer, great to give back to the community :)
Oct 28, 2024 Our paper on attention-guided masked autoencoders is accepted at WACV 2025! :tada: This was joint work with Dominik Engel, Pedro Hermosilla and Timo Ropinski.
May 13, 2024 I’m co-author on great work by Dominik Engel on self-supervised vision transformers for segmentation-based transfer function design, which was accepted at TVCG! :tada:
Feb 28, 2024 My first author paper on depth-guided unsupervised semantic segmentation is accepted at CVPR 2024! :tada: :rocket: :sparkles: Joint work with Dominik Engel, Pedro Hermosilla and Timo Ropinski.

publication highlights

2025

  1. cuts3d-preview.png
    CutS3D: Cutting Semantics in 3D for 2D Unsupervised Instance Segmentation
    Leon Sick, Dominik Engel, Sebastian Hartwig, Pedro Hermosilla, and Timo Ropinski
    arXiv preprint, 2025
    arXiv HTML
  2. attg-preview.png
    Attention-Guided Masked Autoencoders for Learning Image Representations
    Leon Sick, Dominik Engel, Pedro Hermosilla, and Timo Ropinski
    In Oral Presentation, Proceedings of the Winter Conference on Applications of Computer Vision (WACV), Feb 2025
    arXiv HTML

2024

  1. depthg-preview.png
    Unsupervised Semantic Segmentation Through Depth-Guided Feature Correlation and Sampling
    Leon Sick, Dominik Engel, Pedro Hermosilla, and Timo Ropinski
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2024
    arXiv HTML
  2. tttkd-preview.png
    TTT-KD: Test-Time Training for 3D Semantic Segmentation through Knowledge Distillation from Foundation Models
    Lisa Weijler, Muhammad Jehanzeb Mirza, Leon Sick, Can Ekkazan, and Pedro Hermosilla
    International Conference on 3D Vision (3DV), Jun 2024
    arXiv
  3. wscd-preview.png
    Weakly Supervised Virus Capsid Detection with Image-Level Annotations in Electron Microscopy Images
    Hannah Kniesel, Leon Sick, Tristan Payer, Tim Bergner, Kavitha Sshaga Devan, and 4 more authors
    International Conference on Learning Representations (ICLR), Jun 2024
    HTML

2023

  1. ntf-preview.png
    Leveraging Self-Supervised Vision Transformers for Neural Transfer Function Design
    Dominik Engel, Leon Sick, and Timo Ropinski
    Transactions On Visualization and Computer Graphics (TVCG), Jun 2023
    arXiv