Rembert Daems
Computer vision and machine learning researcher
I'm currently at an early-stage medtech startup; before that I was a postdoc in the group of Thomas Demeester. My PhD was on the intersection of visual perception, (stochastic) dynamical systems and physics priors. I started ongoing collaborations with Tolga Birdal and Manfred Opper on SDEs driven by fractional Brownian motion, leading to an ICLR spotlight, and subsequent work led by Gabriel Nobis on generative fractional diffusion models and fractional Schrödinger bridges.
During my PhD I co-founded Hippo Dx, a medical-device start-up behind the automated skin prick test (SPAT), where I worked on the camera and lighting system, image processing and AI-assisted diagnostics. Before my PhD I worked as innovation engineer at CNH Industrial on combine-harvester automation, and as AI lead at Octinion on agricultural computer vision projects.
I live in Brugge with my wife and three kids.
News
- Jul 2026 I joined an early-stage medtech startup (still in stealth mode).
- Oct 2025 SPAT AI readout method published in Nature Communications.
- Sep 2025 Fractional Diffusion Bridge Models accepted at NeurIPS 2025.
- Jun 2025 I defended my PhD thesis, Learning from Video in Continuous Time Using Physics Priors and Fractional Noise.
- Dec 2024 Generative Fractional Diffusion Models at NeurIPS 2024.
- May 2024 Variational Inference for SDEs Driven by Fractional Noise, ICLR spotlight.
Selected publications
Full list on Google Scholar.
Gabriel Nobis, Maximilian Springenberg, Arina Belova, Rembert Daems, Christoph Knochenhauer, Manfred Opper, Tolga Birdal, Wojciech Samek
Advances in Neural Information Processing Systems (NeurIPS), 2025
A generative diffusion-bridge framework driven by an approximation of non-Markovian fractional Brownian motion, capturing the memory and long-range dependence that standard Brownian-motion bridges miss.
Peter De Roovere, Rembert Daems, Jonathan Croenen, Francis wyffels
Machine Vision and Applications, 2025
A three-stage method for 6D pose estimation of texture-less industrial objects: predicting center and curvature heatmaps with a fully convolutional network, triangulating 3D object centers across views, then refining poses by render-and-compare; it reaches millimeter-level, state-of-the-art accuracy on T-LESS and is deployed in a real robotic pick-and-place system.
Sven F. Seys, Valérie Hox, Adam M. Chaker, Glynnis De Greve, Winde Lemmens, Anne-Lise Poirrier, Eline Beckers, Rembert Daems, Zuzana Diamant, Carmen Dierickx, Peter W. Hellings, Caroline Huart, Claudia Jerin, Mark Jorissen, Dirk Loeckx, Hanne Oscé, Karolien Roux, Mark Thompson, Sophie Tombu, Saartje Uyttebroek, Andrzej Zarowski, Senne Gorris, Laura Van Gerven
Nature Communications, 2025
An AI-assisted readout method that measures wheal diameters from Skin Prick Automated Test (SPAT) images, validated against physician measurements, to support consistent allergy diagnosis.
Gabriel Nobis, Maximilian Springenberg, Marco Aversa, Michael Detzel, Rembert Daems, Roderick Murray-Smith, Shinichi Nakajima, Sebastian Lapuschkin, Stefano Ermon, Tolga Birdal, Manfred Opper, Christoph Knochenhauer, Luis Oala, Wojciech Samek
Advances in Neural Information Processing Systems (NeurIPS), 2024
The first continuous-time score-based generative model driven by fractional diffusion: replacing Brownian motion with fractional Brownian motion (Hurst index H) for better diversity and convergence.
Rembert Daems, Manfred Opper, Guillaume Crevecoeur, Tolga Birdal
The Twelfth International Conference on Learning Representations (ICLR), 2024
The first variational inference framework for non-Markovian neural SDEs driven by fractional Brownian motion, approximating the fBM by a linear combination of Markov processes; derives the variational posterior and ELBO.
Rembert Daems, Jeroen Taets, Guillaume Crevecoeur, Francis wyffels
Neurocomputing, 2024
Learns Lagrangian dynamics from images: keypoints give Cartesian coordinates with explicit holonomic constraints, trained unsupervised end-to-end, enabling long-term video prediction and energy-based control.
Rembert Daems, Francis wyffels
Differential Geometry meets Deep Learning (DiffGeo4DL NeurIPS Workshop), 2020
An unsupervised method to learn the orientation of symmetric objects in images, mapping in-plane rotations into an autoencoder's latent space via a crossing loss, disentangling orientation from other factors.Other stuff
An interactive talk that builds fractional Brownian motion up from first principles, with live in-browser demos. My talk for the Ghent Workshop on Machine Learning and Biology (2026).
A practical, hands-on introduction to stochastic differential equations (SDEs), with self-contained example code in JAX and Diffrax.
Runs entirely in your browser (all inference in the frontend) and gives live feedback on your sitting posture. We made this during COVID for the Full Stack Deep Learning course.