PFPhillipp Fanta-Jende

Phillipp Fanta-Jende

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Phillipp Fanta-Jende has a total of 44 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Towards more efficient forest monitoring: A validated pipeline for UAV-ULS forest point cloud stratification and rejuvenation layer mapping

    by Javier Gibran Apud Baca, Jules Salzinger, Phillipp Fanta-Jende, Matthias Lampert, Benjamin Schumacher, Ursula Knieling, Felix Bruckmüller

  • Open Access

    Real-time visual-inertial orthomosaic surface generation and segmentation pipeline for disaster response

    by Marc Haubenstock, Jules Salzinger, Michael Schwingshackl, Felix Bruckmüller, Christoph Sulzbachner, Phillipp Fanta-Jende

  • Open Access

    Using textureless, low-detailed 3D city models for visual localization

    by Yasmin Loeper, Markus Gerke, Phillipp Fanta-Jende

    Accurate camera pose estimation in urban environments remains challenging when reference imagery is generated from low-detailed, textureless 3D city models and must be matched against real world imagery. In this work we (i) extend our existing iterative object-basesd visual localization approach with an additional semantic feature and (ii) conduct a systematic baseline study of contemporary feature matching techniques on such cross-domain query-reference image pairs. As a first step to close the domain gap, we augment our iterative object-based visual localization pipeline with semantic masks derived from a pretrained semantic segmentation model. Intersection-over-Union between query and rendered masks is incorporated into the matching score, leading to a better pose accuracy. For the baseline study, we use a range of feature matching techniques: handcrafted (SIFT, AKAZE, ORB, FAST), learned detectors (XFeat, Key.Net, DeDoDe, DISK, AffNet), learned descriptors (XFeat, DISK, DeDoDe, HardNet), learned matchers (LightGlue, LoFTR), the line matcher SOLD2, and the learned matchers MINIMA-RoMa, MINIMA-LoFTR, MINIMA-XoFTR, and MatchAnything, which were trained on cross-modality datasets. The cross-modality focused matchers achieved the best results. For 20% 10%, 9%, and 7% of the evaluated query images the estimated camera pose had a translation error less than 5m and a rotation error less than 5◦. In this context, the other methods were only able to achieve a maximum success rate of 1.4%.

  • Open Access

    An Analysis of the Impact of Geospatial Data Sources on Mesh-Based Localisation Performance

    by Francesco Vultaggio, Phillipp Fanta-Jende, Alexander Kern, Markus Gerke

    This paper investigates how the provenance and resolution of geospatial data used to construct mesh maps affect the accuracy and robustness of mesh-based visual localisation. Mesh-based approaches offer significant advantages over traditional pipelines reliant on Structure from Motion (SfM) models, including the ability to scale to city-sized scenes—by leveraging large-scale data sources such as national mapping databases— and on-demand generation of arbitrary synthetic views. While prior work has focused on algorithmic improvements to mesh-based localisation, none has systematically analysed how different input data affect localisation outcomes. In this work, we evaluate three meshes—derived from aerial oblique imagery, combined aerial and ground mobile mapping data, and close-range ground imagery—across the egenioussBench Extended and House of Science query sets and four image matchers. We show that mesh quality is the dominant factor governing localisation performance. In the House of Science experiments, aerial meshes lack the resolution required to resolve fac¸ade detail, causing near-total localisation failure regardless of matcher. In the egenioussBench Extended experiments, augmenting an aerial mesh with ground data yields consistent but less dramatic improvements. We further introduce the Perceptual Detail Score (PDS), a viewing-condition-aware metric that proves to be a strong predictor of downstream pose accuracy across all experimental configurations.

  • Open Access

    deSEO: Physics-Aware Dataset Creation for High-Resolution Satellite Image Shadow Removal

    by Lorenzo Beltrame, Jules Salzinger, Filip Svoboda, Phillipp Fanta-Jende, Jasmin Lampert, Radu Timofte, Marco Körner

    Shadows cast by terrain and tall structures remain a major obstacle for high-resolution satellite image analysis, degrading classification, detection, and 3D reconstruction performance. Public resources offering geometry-consistent paired shadow/shadow-free satellite imagery are essentially missing, and most Earth-observation datasets are designed for shadow detection or 3D modelling rather than removal. Existing deep shadow-removal datasets either target ground-level or aerial scenes or rely on unpaired and weakly supervised formulations rather than explicit satellite pairs. We address this gap with deSEO, a geometry-aware and physics-informed methodology that, to the best of our knowledge, is the first to derive paired supervision for satellite shadow removal from the S-EO shadow detection dataset (Masquil et al., 2025) through a fully replicable pipeline. For each tile, deSEO selects a minimally shadowed acquisition as a weak reference and pairs it with shadowed counterparts using temporal and geometric filtering, Jacobian-based orientation normalisation, and LoFTR–RANSAC registration. A per-pixel validity mask restricts learning to reliably aligned regions, enabling supervision despite residual off-nadir parallax. In addition to this paired dataset, we develop a DSM-aware deshadowing model that combines residual translation, perceptual objectives, and mask-constrained adversarial learning. In contrast, a direct adaptation of a UAV-based SRNet/pix2pix architecture fails to converge under satellite viewpoint variability. Our model consistently reduces the visual impact of cast shadows across diverse illumination and viewing conditions, achieving improved structural and perceptual fidelity on held-out scenes. deSEO therefore provides the first reproducible, geometry-aware paired dataset and baseline for shadow removal in satellite Earth observation.

  • Open Access

    Conflict Detection, Resolution, and Collision Avoidance for Decentralized UAV Autonomy: Classical Methods and AI Integration

    by Francesco D’apolito, Phillipp Fanta-Jende, Verena Widhalm, Christoph Sulzbachner

    Unmanned Aerial Vehicles (UAVs) are increasingly deployed across diverse domains. Many applications demand a high degree of automation, supported by reliable Conflict Detection and Resolution (CD&R) and Collision Avoidance (CA) systems. At the same time, public mistrust, safety and privacy concerns, the presence of uncooperative airspace users, and rising traffic density are increasing research interest toward decentralized concepts such as free flight, in which each actor is responsible for its own safe trajectory. This survey reviews CD&R and CA methods with a particular focus on decentralized automation. It analyzes qualitatively classical rule-based approaches and their limitations, then examines machine learning (ML)-based techniques that aim to improve adaptability in complex environments. Building on recent regulatory discussions, it further considers how requirements for trust, transparency, explainability, and interpretability evolve with the degree of human oversight and autonomy, addressing gaps left by prior surveys.


  • Open Access

    egenioussBench: A New Dataset for Geospatial Visual Localisation

    by Phillipp Fanta-Jende, Francesco Vultaggio, Alexander Kern, Yasmin Loeper, Markus Gerke

    We present egenioussBench, a visual localisation benchmark built on geospatial reference data: a city-scale airborne 3D mesh and a CityGML LoD2 model. This pairing reflects deployable mapping assets and supports true scalability beyond traditional SfM-based approaches. The query data comprise smartphone images with centimetre-accurate, map-independent ground truth obtained via PPK and GCP/CP-aided adjustment. From 2,709 images, we derive a non-co-visible subset by estimating the full co-visibility matrix from rendered depth and selecting a maximum independent set; the released data include a test split of 42 non-co-visible images with withheld ground truth and a validation split of 412 sequential images with poses, e.g. for training of pose regressors and self-validation. The benchmark features a public leaderboard evaluated with binning metrics at multiple pose-error thresholds alongside global statistics (median, RMSE, outlier ratio), ensuring fair, like-for-like comparison across mesh- and LoD2-based methods. Together, these design choices expose realistic cross-view and cross-domain challenges while providing a rigorous, scalable path for advancing large-scale visual localisation. We make the evaluation code and data availeable at https://github.com/fratopa/egenioussBench and https://www.egeniouss.eu/


  • Open Access

    Conflict Detection, Resolution, and Collision Avoidance for Decentralized UAV Autonomy: Classical Methods and AI Integration

    by Francesco D’apolito, Phillipp Fanta-Jende, Verena Widhalm, Christoph Sulzbachner

    Unmanned Aerial Vehicles (UAVs) are increasingly deployed across diverse domains and many applications demand a high degree of automation, supported by reliable Conflict Detection and Resolution (CD&R) and Collision Avoidance (CA) systems. At the same time, public mistrust, safety and privacy concerns, the presence of uncooperative airspace users, and rising traffic density are driving a shift toward decentralized concepts such as free flight, in which each actor is responsible for its own safe trajectory. This survey reviews CD&R and CA methods with a particular focus on decentralized automation and encounters with noncooperative intruders. It analyzes classical rule-based approaches and their limitations, then examines Machine Learning (ML)–based techniques that aim to improve adaptability in complex environments. Building on recent regulatory discussions, it further considers how requirements for trust, transparency, explainability, and interpretability evolve with the degree of human oversight and autonomy, addressing gaps left by prior surveys.

  • Open Access

    Advancements on Semantic Real-Time UAV Mapping

    by Marc Haubenstock, Jules Salzinger, Michael Schwingshackl, Felix Bruckmüller, Christoph Sulzbachner, Phillipp Fanta-Jende

    This paper presents key improvements in real-time ortho image generation and scene understanding for disaster management and first responders. Through the introduction of an Inertial Measurement Unit, a depth estimation network and a trained network for scene segmentation, it is possible to produce end-to-end real-time ortho and semantic maps. Since datasets containing inertial data are sparse, the results of the pipeline were verified on a flight, which was recorded and post-processed as a ground truth with ground control points using the standard photogrammetric workflow. The reported errors are in the same range as a post-processed ortho map on raw Global Navigation Satellite System measurements, however, produced in real time. Semantic segmentation results demonstrate surprising levels of accuracy and robustness, but reveal a need for more comprehensive data acquisitions and benchmarks.

  • Open Access

    ResQDrone: Autonomous Indoor Quadcopter for Multi-Layered Mapping in Crisis and Disaster Management Scenarios

    by Marco Cella, Jürgen Biber, Pierrick Bournez, Jules Salzinger, Verena Widhalm, Francesco Vultaggio, Francesco D’aPolito, Felix Bruckmüller, Christoph Sulzbachner, Phillipp Fanta-Jende

    This paper introduces a fully autonomous quadcopter developed for the safe and efficient exploration of indoor environments in crisis and disaster management scenarios. These environments are typically partially destroyed, entirely unknown, and suffer from restricted visibility. During exploration, multiple mapping layers are generated and transmitted to human operators in real-time, delivering critical insights into the structure. These layers include geometric, semantic, and thermal maps, each contributing distinct information: the geometric layer provides a precise volumetric layout; the semantic layer enriches this layout with contextual understanding of different structural classes; the thermal layer highlights relevant signatures — e.g., humans — that support timely and informed intervention. Successful tests in controlled and simplified real-world environments demonstrate the system’s robustness and its practical value in operational contexts.