Jakob Nazarenus

We propose a method to reconstruct dynamic fire in 3D from a limited set of camera views with a Gaussian-based spatiotemporal representation. Capturing and reconstructing fire and its dynamics is highly challenging due to its volatile nature, transparent quality, and multitude of high-frequency features. Despite these challenges, we…

Type

Conference paper

Topics

Gaussian splatting · dynamic reconstruction · fire

Omnidirectional capture of dynamic scenes facilitates the creation of immersive virtual reality assets and holistic scene understanding. Outward-facing multi-fisheye camera rigs offer an efficient solution for full-scene coverage, using fewer lenses than conventional pinhole arrays while enabling all-directional observation of…

Type

Journal article

Topics

dynamic scenes · omnidirectional · priors

Monitoring robotic manipulators is essential in highly automated environments, where optical cameras can provide precise and dense information while suffering from line-of-sight occlusions. This paper introduces a lightweight, learning-based solution to address these occlusions in robot-camera systems. We employ a small MLP…

Type

Journal article

Topics

robotics · Gaussian splatting · manipulation

Consumer-level omnidirectional video offers an economically viable means to create virtual reality (VR) assets, enabling users to explore and interact within a fully immersive visual environment. However, editing such videos, particularly those with 360° views and dynamic objects, poses significant challenges. Existing approaches to…

Type

Journal article

Topics

dynamic scenes · omnidirectional · representation

During a multi-stage press hardening process, where a metal sheet undergoes rapid austenitization, tempering, and forming, the spatial-temporal temperature development is a driving factor and its control enables it to reach desired product properties. A two-dimensional model extension is proposed, which enables a precise and…

Type

Conference paper

Topics

estimation · manufacturing · thermal

Due to recent advances in 3D reconstruction from RGB images, it is now possible to create photorealistic representations of real-world scenes that only require minutes to be reconstructed and can be rendered in real time. In particular, 3D Gaussian splatting shows promising results, outperforming preceding reconstruction methods while…

Type

Journal article

Topics

Gaussian splatting · camera models · optics

In many applications, robotic systems are monitored via camera systems. This helps with monitoring automated production processes, anomaly detection, and the refinement of the estimated robot’s pose via optical tracking systems. While providing high precision and flexibility, the main limitation of such systems is their line-of-sight constraint. In this paper, we propose a lightweight solution for automatically learning this occluded space to provide continuously observable robot trajectories. This is achieved by an initial autonomous calibration procedure and subsequent training of a simple neural network. During operation, this network provides a prediction of the visibility status with a balanced accuracy of 90% as well as a gradient that leads the robot to a more well-observed area. The prediction and gradient computations run with sub-ms latency and allow for modular integration into existing dynamic trajectory-planning algorithms to ensure high visibility of the desired target.

Type

Conference paper

Topics

robotics · occlusion · learning

Medical phantoms mimic aspects of procedures like computed tomography (CT), ultrasound (US) imaging, and surgical practices. However, the materials for current commercial phantoms are expensive and the fabrication with these is complex and lacks versatility. Therefore, existing material solutions are not suitable for creating…

Type

Journal article

Topics

medical imaging · phantoms · materials

High-quality data is crucial for the success of machine learning, but labeling large datasets is often a time-consuming and costly process. While semi-supervised learning can help mitigate the need for labeled data, label quality remains an open issue due to ambiguity and disagreement among annotators. Thus, we use proposal-guided…

Type

Book chapter

Topics

annotation · classification · data quality

Hyperfluorescence (HF) and reduced autofluorescence (RA) are important biomarkers in fundus autofluorescence images (FAF) for the assessment of health of the retinal pigment epithelium (RPE), an important indicator of disease progression in geographic atrophy (GA) or central serous chorioretinopathy (CSCR). Autofluorescence images…

Type

Journal article

Topics

medical imaging · segmentation · ensemble

Sector

Mediation · non-profit

Period

2026

Stack

SvelteKit · LangChain · AWS Bedrock · Postgres

Site

mikk-ev.org

Sector

Healthcare · controlling

Period

2026

Stack

SvelteKit · Python · Postgres

Sector

B2B · IT network

Period

2019 · 2026

Outcome

1,000+ qualified leads

Stack

SvelteKit · Python · GCP · Postgres

Site

www.cpn.network

Sector

Public sector

Period

2025

Outcome

Thousands of regular users

Stack

Svelte · Django · Azure

Site

www.armee.ch

Sector

Public sector

Period

2025

Stack

Svelte · Django · Azure

Site

www.esa.admin.ch/de/esi-chatbot-der-esa

Domain

Embedded / RF

Built with

LoRa · mesh protocol · encryption · enclosure design

Domain

Embedded / IoT

Built with

ESP32 · e-ink · low-power · central server

Domain

IoT / security

Built with

Home Assistant · access control · web

Domain

Hardware / 3D

Built with

Matter · Thread · home automation · 3D design