Remco Royen

I am a Postdoctoral Computer Vision Researcher at the Vrije Universiteit Brussel. I completed my PhD in Engineering Sciences in June 2024 under the supervision of Prof. Adrian Munteanu. My doctoral research included important practical applications and involved close collaborations with companies such as Xenomatix, Sabca and VoxelSensors. Our work with VoxelSensors resulted in a patent. I was also awarded a PhD fellowship for strategic basic research by the Research Foundation Flanders (FWO).

Research interests are in 3D computer vision, deep learning, and point cloud processing. Most of my research has been focused on 3D scene understanding and the introduction of scalability to deep learning. Recently, I have also developed an interest in the impressive development of view synthesis methods and its connection with existing 3D processing methods.

Email  /  CV  /  LinkedIn  /  Google Scholar  /  GitHub

News

Education

Publications

*Indicates Equal Contribution

The first generalizable semantic segmentation method employing Gaussian Splatting. Our method is not only superior in segmentation quality, but also achieves real-time performance of 27 FPS, marking an astonishing 901 times speedup compared to the SOTA.

A 3D instance segmentation method which simultaneously learns coefficients and prototypes. The obtained prototypes are visualizable and interpretable. Experiments on S3DIS-blocks and PartNet.

A significant improvement in performance over RESSCAL3D: resolution scalable 3D semantic segmentation + a new dataset VX-S3DIS exhibiting resolution scalable point streams with semantic labels.

A 3D instance segmentation method which simultaneously learns coefficients and prototypes. The obtained prototypes are visualizable and interpretable.

1) The presentation of a new highly realistic synthetic traffic dataset, SynthV6D, for 6D pose estimation. 2) A weakly-supervised domain adaptation approach for 6D pose estimation of vehicles.

A fully parallelizable vector-quantized variational autoencoder model (VQVAE) that generates high-quality point clouds in milliseconds.

Resolution-scalable 3D semantic segmentation of point clouds. By enabling the processing of different resolution scales in parallel, RESSCAL3D is 31-62% faster than the non-scalable baseline and allows early predictions.

A GPU-accelerated simulator that enables the generation of high-quality, perfectly labelled data for any Time-of-Flight sensor, including LiDAR.

An improvement over Mono6D by the introduction of point cloud visibility prediction.

A new block merging algorithm suitable for any block-based 3D instance segmentation technique. It significantly and consistently improves the obtained accuracy for all evaluation metrics employed in literature, regardless of the underlying network architecture.

The first deep-learning-based approach to automatic foot measurement extraction from a single 3D scan.

A monocular approach for vehicle pose estimation using vehicle 3D priors provided by vehicle make-and-model recognition methods to estimate the 6D pose.

A new neural network layer. It can be integrated in any feedforward network, allowing quality scalability by design by creating embedded feature sets.

Additional academic activities

• Machine Learning and Big Data Processing - 2021, 2022, 2023, 2024
• Sensors and Microsystem Electronics - 2020

• Mihnea-Bogdan Jurca - Real-Time Generalizable Semantic Segmentation For 3D Gaussian Representations of Radiance Fields - 2024
• Madina Myrzaliyeva - Investigating The Impact Of Climate Change On Weather Regimes Using Dimensionality Reduction With Deep Autoencoders - 2022
• Jasper De Coninck - View Synthesis For Light Field Camera Arrays - 2022