I am a creative and fun individual with a passion for visual arts and technology. With a multidisciplinary background ranging from high-end hospitality to architecture and computer science, I bring a unique perspective to every project I undertake.
I’m driven by a personal vision of a sustainable future, where I hope to bring my contribution with products and services that elevate experiences for users and helps conserve the environment.
My approach to my work is always user-centric, informed by my architectural training and my understanding of how spaces, both physical and digital, shape our interactions.
Outside of work, you might find me doing Crossfit, traveling, looking at buildings or talking about cinema, always on the lookout for new sources of inspiration. The only limits to our creativity are the ones we impose ourselves, and I’m excited for my life-long journey at the intersection of art, design, and technology with as fewer limits as possible.
2024
co-author(s): Stella Graßhof
In a highly digitalised world, this paper aims at closing the gap towards automatic digitisation from 2D architectural drawings. We present the new image dataset Plan, and Elevation Representations of Doors And Windows (Perdaw) which provides a baseline for different classification problems with varying complexity. We investigate the per formance of three machine learning models in distinguishing different types of doors and windows in their plan and elevation views. Our findings show that Inception V3 slightly outperforms MobileNet V2, which suggests that the latter solves the same classification tasks with less computational resources with only a minimal compromise in accuracy. Among the three investigated models, ResNet50 yields the lowest quality metrics within a small margin. Overall, all models perform better at classifying building components in their elevation views compared to their plan views. We consistently observed that the models yield the best results with 100% accuracy for the binary classification problems, and dropped to close to 70% accuracy for the 40-class classification problems.
2023
The following Research Paper sets out to investigate possible solution for an automatized 3D Reconstruction method based on architectural floor plans. Having an emphasis on Computer Science, the paper sets out to explore the larger context of the topic through astructured literature review whilst also presenting terminologies and prevalent technologies within the architecture, engineering and construction (AEC) field, as well as the relationships and dependencies between them. The second part of the paper focuses on the process of experimentation with different Computer Vision and Optical Character Recognition libraries, in an attempt to design and test an initial reconstruction program prototype from a 2D architectural floor plan onto a 3D environment. Finally, the paper concludes with the literature review, the results of the implementations, and key takeaways and sets a course for future work.
Founder & Principal Developer
July 2024 - Present
Fitras App
A cross-platform Functional Fitness Recording & Analytics mobile application for Arca users.
Founder & Principal Consultant
March 2024 - Present
Zmei Consulting
An IT-Consulting company, specialized in IT strategy, Software Architecture & Development.
Product Lead & Project Manager
February 2024 - September
TrustNet
TrustNet is a cross-platform trust and security broker, working on the OpenID Connect & Fido2/WebAuthn standards for authentication and authorization.