Musicons is a novel visualisation of music to improve user-guided search and exploration. The visualisation is based on latent variable representations and allows users to visually identify similarity between songs. This project was done as part of my master thesis at the Delft University of Technology. Find the demo on musicons.io or read my full thesis here.

At the Programme Innovation of Mathemathics Education of the Delft University of Technology, I was part of the visuals team that made visualisations of mathematical concepts. Our novel interactive animation method was presented at the ACM Web3D conference, read the publication or check out the interactive poster.

An investigation of the performance of three popular image segmentation models on the task of segmenting images of various kinds of litter. Read the report on the experiments or check out the code and pre-trained models

Motion Magnification is the process of magnifying subtle, microscopic amounts of motion in a video sequence to the point where the eye can detect the motion. I have made a full implementation in Matlab of the original 2005 paper that first explained the basis for this method. Check out the full code or watch the demo video.

My bachelor graduation thesis took place at the Borges 3D company I developed inpainting neural networks to accelerate rendering. Watch the demo video or read the full report.

As part of the honours programme during my BSc, I implemented a global illumination radiosity renderer that supports fluorescent materials. The renderer applies the radiosity method and uses spectral rendering in order to simulate fluorescent materials: materials can reflect energy of a given frequency at another frequency. Rendering is accelerated by NVIDIA OptiX and CUDA parallelization. Source code can be found here, the report here.