Dominik Engel

Deep Learning Researcher

Biography

Hi, I’m Dominik. Currently I do research on deep learning on visual data. Previously I got my PhD at Ulm University in the Visual Comptuing Group, working at the intersection of deep learning and volume rendering. Also I really love coding, coffee, linux, games and all kinds of funky tech.

Interests

Artificial Intelligence
Computer Graphics
Computer Vision

Education

PhD in Computer Science, 2024
Ulm University
MSc in Media Informatics, 2018
Ulm University
BSc in Computer Science, 2016
Ulm University

Publications

ARCOL: Aspect Ratio Constrained Orthogonal Layout

Zainab Alsuwaykit, Yousef Rajeh, Alexandre Kouyoumdjian, Steve Kieffer, Dominik Engel, Sara Di Bartolomeo, Martin Nöllenburg, Ivan Viola (2026). ARCOL: Aspect Ratio Constrained Orthogonal Layout. Computer Graphics Forum (CGF).

Cite DOI Paper arXiv

EfficientMonoHair: Fast Strand-Level Reconstruction from Monocular Video via Multi-View Direction Fusion

Da Li, Dominik Engel, Deng Luo, Ivan Viola (2026). EfficientMonoHair: Fast Strand-Level Reconstruction from Monocular Video via Multi-View Direction Fusion. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

Cite DOI Paper arXiv Code

ClickAIXR: On-Device Multimodal Vision-Language Interaction with Real-World Objects in Extended Reality

Dawar Khan, Alexandre Kouyoumdjian, Xinyu Liu, Omar Mena, Dominik Engel, Ivan Viola (2026). ClickAIXR: On-Device Multimodal Vision-Language Interaction with Real-World Objects in Extended Reality. arXiv preprint (arXiv).

Cite DOI arXiv

Da Li, Donggang Jia, Yousef Rajeh, Dominik Engel, Ivan Viola (2025). RaRa Clipper: A Clipper for Gaussian Splatting Based on Ray Tracer and Rasterizer. Proceedings of the SIGGRAPH Asia Conference Papers (SIGGRAPH Asia).

Cite DOI Paper arXiv Code

S2D: Sparse-To-Dense Keymask Distillation for Unsupervised Video Instance Segmentation

Leon Sick, Lukas Hoyer, Dominik Engel, Pedro Hermosilla, Timo Ropinski (2025). S2D: Sparse-To-Dense Keymask Distillation for Unsupervised Video Instance Segmentation. arXiv preprint (arXiv).

Cite DOI arXiv Project Code

A Survey on Quality Metrics for Text-to-Image Generation

Sebastian Hartwig, Dominik Engel, Leon Sick, Hannah Kniesel, Tristan Payer, Poonam Poonam, Michael Glöckler, Alex Bäuerle, Timo Ropinski (2025). A Survey on Quality Metrics for Text-to-Image Generation. IEEE Transactions on Visualization and Computer Graphics (TVCG).

Cite DOI Paper arXiv

CutS3D: Cutting Semantics in 3D for 2D Unsupervised Instance Segmentation

Leon Sick, Dominik Engel, Sebastian Hartwig, Pedro Hermosilla, Timo Ropinski (2025). CutS3D: Cutting Semantics in 3D for 2D Unsupervised Instance Segmentation. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV).

Cite DOI Paper arXiv Project

Leon Sick, Dominik Engel, Pedro Hermosilla, Timo Ropinski (2025). Attention-Guided Masked Autoencoders for Learning Image Representations. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV).

Cite DOI Paper arXiv Project Code

HPSCAN: Human Perception-Based Scattered Data Clustering

Sebastian Hartwig, Christian Van Onzenoodt, Dominik Engel, Pedro Hermosilla, Timo Ropinski (2025). HPSCAN: Human Perception-Based Scattered Data Clustering. Computer Graphics Forum (CGF).

Cite DOI Paper arXiv Code

Unsupervised Semantic Segmentation Through Depth-Guided Feature Correlation and Sampling

Leon Sick, Dominik Engel, Pedro Hermosilla, Timo Ropinski (2024). Unsupervised Semantic Segmentation Through Depth-Guided Feature Correlation and Sampling. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

Cite DOI Paper arXiv Project Code