Remco Royen

Mr. Remco Royen

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 May 2021 in Neural Networks
Verified
Journal Article
Closed access
RRRemco Royen
Remco Royen
LDLeon Denis
Leon Denis
QBQuentin Bolsee
Quentin Bolsee
Pengpeng HuPengpeng Hu
Pengpeng Hu
AMAdrian Munteanu
Adrian Munteanu

28 September 2023 in Sensors
Verified
Journal Article
Open access
PDF file
LDLeon Denis
Leon Denis
RRRemco Royen
Remco Royen
QBQuentin Bolsée
Quentin Bolsée
NVNicolas Vercheval
Nicolas Vercheval
Aleksandra PižuricaAleksandra Pižurica
Aleksandra Pižurica
Adrian MunteanuAdrian Munteanu
Adrian Munteanu
High-quality data are of utmost importance for any deep-learning application. However, acquiring such data and their annotation is challenging. This paper presents a GPU-accelerated simulator that enables the generation of high-quality, perfectly labelled data for any Time-of-Flight sensor, including LiDAR. Our approach optimally exploits the 3D graphics pipeline of the GPU, significantly decreasing data generation time while preserving compatibility with all real-time rendering engines. The presented algorithms are generic and allow users to perfectly mimic the unique sampling pattern of any such sensor. To validate our simulator, two neural networks are trained for denoising and semantic segmentation. To bridge the gap between reality and simulation, a novel loss function is introduced that requires only a small set of partially annotated real data. It enables the learning of classes for which no labels are provided in the real data, hence dramatically reducing annotation efforts. With this work, we hope to provide means for alleviating the data acquisition problem that is pertinent to deep-learning applications.

26 February 2024 in Electronics Letters
Verified
Journal Article
Open access
RRRemco Royen
Remco Royen
LDLeon Denis
Leon Denis
Adrian MunteanuAdrian Munteanu
Adrian Munteanu
3D instance segmentation is crucial for applications demanding comprehensive 3D scene understanding. Here, a novel method is introduced that simultaneously learns coefficients and prototypes. Employing an overcomplete sampling strategy, the method produces an overcomplete set of instance predictions, from which the optimal ones are selected through a Non‐Maximum Suppression (NMS) algorithm during inference. The obtained prototypes are visualizable and interpretable. The method demonstrates superior performance on S3DIS‐blocks, consistently outperforming existing methods in mRec and mPrec. Moreover, it operates 32.9% faster than the state‐of‐the‐art. Notably, with only 0.8% of the total inference time, the method exhibits an over 20‐fold reduction in the variance of inference time compared to existing methods. These attributes render the method well‐suited for practical applications requiring both rapid inference and high reliability.

21 February 2024 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
YLYangxintong Lyu
Yangxintong Lyu
RRRemco Royen
Remco Royen
Adrian MunteanuAdrian Munteanu
Adrian Munteanu
Synthetic traffic datasets provide highly accurate and affordable annotations, which are of crucial importance in complex vision-based perception tasks performed on real-world traffic data. Due to the lack of paired 2D-3D data, it remains very challenging when adapting the knowledge of a vehicle’s pose in SE (3) with its known 3D geometry. In this paper, we firstly propose a synthetic dataset, SynthV6D, enabling 6D pose estimation of vehicles in monocular traffic images. The dataset comprises industrial-grade vehicles in motion evolving in realistic virtual scenery, covering a wide range of viewpoints and distances. Secondly, we introduce a weakly-supervised domain adaptation approach, dubbed W6DNet, to recover the 6D pose. To this end, by using the synthetic dataset, a novel linked image feature space-based domain adaptation is introduced. Furthermore, an original two-step Double-Fusion block is proposed to fuse the multi-modal data representations and the cross-space features. Consequently, the proposed method learns the pose-specific embeddings. We evaluate W6DNet on the real-world ApolloCar3D dataset. Extensive experimental results demonstrate that, when a small amount of real-world data is accessible, the proposed approach can significantly advance the performance when adapting knowledge from SynthV6D. Moreover, it achieves competitive performance compared to fully supervised state-of-the-art methods.

23 February 2026 in Signal Processing: Image Communication
Verified
Journal Article
Closed access
RRRemco Royen
Remco Royen
LDLeon Denis
Leon Denis
AMAdrian Munteanu
Adrian Munteanu

22 February 2024 in Sensors
Verified
Journal Article
Open access
PDF file
NVNicolas Vercheval
Nicolas Vercheval
RRRemco Royen
Remco Royen
Adrian MunteanuAdrian Munteanu
Adrian Munteanu
Aleksandra PižuricaAleksandra Pižurica
Aleksandra Pižurica
Generative models have the potential to revolutionize 3D extended reality. A primary obstacle is that augmented and virtual reality need real-time computing. Current state-of-the-art point cloud random generation methods are not fast enough for these applications. We introduce a vector-quantized variational autoencoder model (VQVAE) that can synthesize high-quality point clouds in milliseconds. Unlike previous work in VQVAEs, our model offers a compact sample representation suitable for conditional generation and data exploration with potential applications in rapid prototyping. We achieve this result by combining architectural improvements with an innovative approach for probabilistic random generation. First, we rethink current parallel point cloud autoencoder structures, and we propose several solutions to improve robustness, efficiency and reconstruction quality. Notable contributions in the decoder architecture include an innovative computation layer to process the shape semantic information, an attention mechanism that helps the model focus on different areas and a filter to cover possible sampling errors. Secondly, we introduce a parallel sampling strategy for VQVAE models consisting of a double encoding system, where a variational autoencoder learns how to generate the complex discrete distribution of the VQVAE, not only allowing quick inference but also describing the shape with a few global variables. We compare the proposed decoder and our VQVAE model with established and concurrent work, and we prove, one by one, the validity of the single contributions.