Mark Bo Jensen

I am an Assistant professor at the Technical University of Denmark. My research is driven by a deep focus on high-performance graphics and advanced visualization. Leveraging over 10 years of expertise in real-time computer graphics, I specialize in building highly optimized rendering solutions capable of processing and visualizing complex data interactively. My work applies these high-performance, real-time rendering capabilities to the field of Extended Reality (XR), creating technologically demanding, immersive, and visually uncompromising experiences that push the boundaries of modern graphics systems.

I was a co-founder of AL-EYE, where we developed software that turned mixed reality headsets with eye tracking into disability aids for people with low vision, hearing loss, or motor disability with the goal of creating a ‘universal disability aids’ that provided multisensory support individualised for each user.

I previously worked as a team lead at Dalux where I oversaw the development of their inhouse Vulkan-based mobile render engine, and I was an external lecturere at the Technical University of Denmark, teaching a course about creating XR-based experiences.

I obtained a Ph.D. in Computer Graphics by doing research that pushes graphics hardware to create high performance Virtual Reality-based visualization of scientific data. Through out my research I have developed a bespoke Vulkan-based 3D engines for VR-based visualization, I am developing a course on XR experiences, and have supervised various Graphics related projects. I have a background as a Technical Artist and Pipeline Engineer in the games and VFX industry before obtaining a MSc in Engineering.

selected publications

StereoDiffusion: Training-Free Stereo Image Generation Using Latent Diffusion Models

Lezhong Wang, Jeppe Revall Frisvad, Mark Bo Jensen, and 1 more author

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Jun 2024

Bib PDF Code

@inproceedings{Wang_2024_CVPR,
  author = {Wang, Lezhong and Frisvad, Jeppe Revall and Jensen, Mark Bo and Bigdeli, Siavash Arjomand},
  title = {StereoDiffusion: Training-Free Stereo Image Generation Using Latent Diffusion Models},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
  month = jun,
  year = {2024},
  pages = {7416-7425},
}

Digitizing translucent object appearance by validating computed optical properties

Duc Minh Tran, Mark Bo Jensen, Pablo Santafé-Gabarda, and 4 more authors

Appl. Opt., Jun 2024

Abs Bib PDF

The optical properties available for an object are most often fragmented and insufficient for photorealistic rendering of the object. We propose a procedure for digitizing a translucent object with sufficient information for predictive rendering of its appearance. Based on object material descriptions, we compute optical properties and validate or adjust this object appearance model based on comparison of simulation with spectrophotometric measurements of the bidirectional scattering-surface reflectance distribution function (BSSRDF). To ease this type of comparison, we provide an efficient simulation tool that computes the BSSRDF for a particular light-view configuration. Even with just a few configurations, the localized lighting in BSSRDF measurements is useful for assessing the appropriateness of computed or otherwise acquired optical properties. To validate an object appearance model in a more common lighting environment, we render the appearance of the obtained digital twin and assess the photorealism of our renderings through pixel-by-pixel comparison with photographs of the physical object.
@article{tran2024Translucent, author = {Tran, Duc Minh and Jensen, Mark Bo and Santaf\'{e}-Gabarda, Pablo and K\"{a}llberg, Stefan and Ferrero, Alejandro and Hannemose, Morten Rieger and Frisvad, Jeppe Revall}, journal = {Appl. Opt.}, keywords = {Absorption coefficient; Bidirectional reflectance distribution function; Camera calibration; Optical properties; Spectral properties; Turbid media}, number = {16}, pages = {4317--4331}, publisher = {Optica Publishing Group}, title = {Digitizing translucent object appearance by validating computed optical properties}, volume = {63}, month = jun, year = {2024}, url = {https://opg.optica.org/ao/abstract.cfm?URI=ao-63-16-4317}, doi = {10.1364/AO.521974}, }

Performance Comparison of Meshlet Generation Strategies

Mark Bo Jensen, Jeppe Revall Frisvad, and J. Andreas Bærentzen

Journal of Computer Graphics Techniques (JCGT), Dec 2023

Bib PDF Code

@article{jensen2023Meshlet,
  author = {Jensen, Mark Bo and Frisvad, Jeppe Revall and B{\ae}rentzen, J. Andreas},
  title = {Performance Comparison of Meshlet Generation Strategies},
  year = {2023},
  month = dec,
  day = {8},
  journal = {Journal of Computer Graphics Techniques (JCGT)},
  volume = {12},
  number = {2},
  pages = {1--27},
  url = {http://jcgt.org/published/0012/02/01/},
  issn = {2331-7418},
}