Patrick Ebel

Fang Xu, Yilei Shi, Patrick Ebel et al.

The challenge of the cloud removal task can be alleviated with the aid of Synthetic Aperture Radar (SAR) images that can penetrate cloud cover. However, the large domain gap between optical and SAR images as well as the severe speckle noise of SAR images may cause significant interference in SAR-based cloud removal, resulting in performance degeneration. In this paper, we propose a novel global-local fusion based cloud removal (GLF-CR) algorithm to leverage the complementary information embedded in SAR images. Exploiting the power of SAR information to promote cloud removal entails two aspects. The first, global fusion, guides the relationship among all local optical windows to maintain the structure of the recovered region consistent with the remaining cloud-free regions. The second, local fusion, transfers complementary information embedded in the SAR image that corresponds to cloudy areas to generate reliable texture details of the missing regions, and uses dynamic filtering to alleviate the performance degradation caused by speckle noise. Extensive evaluation demonstrates that the proposed algorithm can yield high quality cloud-free images and outperform state-of-the-art cloud removal algorithms with a gain about 1.7dB in terms of PSNR on SEN12MS-CR dataset.

Patrick Ebel, Vivien Sainte Fare Garnot, Michael Schmitt et al.

Clouds and haze often occlude optical satellite images, hindering continuous, dense monitoring of the Earth's surface. Although modern deep learning methods can implicitly learn to ignore such occlusions, explicit cloud removal as pre-processing enables manual interpretation and allows training models when only few annotations are available. Cloud removal is challenging due to the wide range of occlusion scenarios -- from scenes partially visible through haze, to completely opaque cloud coverage. Furthermore, integrating reconstructed images in downstream applications would greatly benefit from trustworthy quality assessment. In this paper, we introduce UnCRtainTS, a method for multi-temporal cloud removal combining a novel attention-based architecture, and a formulation for multivariate uncertainty prediction. These two components combined set a new state-of-the-art performance in terms of image reconstruction on two public cloud removal datasets. Additionally, we show how the well-calibrated predicted uncertainties enable a precise control of the reconstruction quality.

Fang Xu, Yilei Shi, Patrick Ebel et al.

Cloud removal is a significant and challenging problem in remote sensing, and in recent years, there have been notable advancements in this area. However, two major issues remain hindering the development of cloud removal: the unavailability of high-resolution imagery for existing datasets and the absence of evaluation regarding the semantic meaningfulness of the generated structures. In this paper, we introduce M3R-CR, a benchmark dataset for high-resolution Cloud Removal with Multi-Modal and Multi-Resolution data fusion. With this dataset, we consider the problem of cloud removal in high-resolution optical remote sensing imagery by integrating multi-modal and multi-resolution information. In this context, we have to take into account the alignment errors caused by the multi-resolution nature, along with the more pronounced misalignment issues in high-resolution images due to inherent imaging mechanism differences and other factors. Existing multi-modal data fusion based methods, which assume the image pairs are aligned accurately at pixel-level, are thus not appropriate for this problem. To this end, we design a new baseline named Align-CR to perform the low-resolution SAR image guided high-resolution optical image cloud removal. It gradually warps and fuses the features of the multi-modal and multi-resolution data during the reconstruction process, effectively mitigating concerns associated with misalignment. In the experiments, we evaluate the performance of cloud removal by analyzing the quality of visually pleasing textures using image reconstruction metrics and further analyze the generation of semantically meaningful structures using a well-established semantic segmentation task. The proposed Align-CR method is superior to other baseline methods in both areas.

Patrick Ebel, Christoph Lingenfelder, Andreas Vogelsang

With modern infotainment systems, drivers are increasingly tempted to engage in secondary tasks while driving. Since distracted driving is already one of the main causes of fatal accidents, in-vehicle touchscreen Human-Machine Interfaces (HMIs) must be as little distracting as possible. To ensure that these systems are safe to use, they undergo elaborate and expensive empirical testing, requiring fully functional prototypes. Thus, early-stage methods informing designers about the implication their design may have on driver distraction are of great value. This paper presents a machine learning method that, based on anticipated usage scenarios, predicts the visual demand of in-vehicle touchscreen interactions and provides local and global explanations of the factors influencing drivers' visual attention allocation. The approach is based on large-scale natural driving data continuously collected from production line vehicles and employs the SHapley Additive exPlanation (SHAP) method to provide explanations leveraging informed design decisions. Our approach is more accurate than related work and identifies interactions during which long glances occur with 68 % accuracy and predicts the total glance duration with a mean error of 2.4 s. Our explanations replicate the results of various recent studies and provide fast and easily accessible insights into the effect of UI elements, driving automation, and vehicle speed on driver distraction. The system can not only help designers to evaluate current designs but also help them to better anticipate and understand the implications their design decisions might have on future designs.

Brandon Victor, Mathilde Letard, Peter Naylor et al.

Floods are among the most common and devastating natural hazards, imposing immense costs on our society and economy due to their disastrous consequences. Recent progress in weather prediction and spaceborne flood mapping demonstrated the feasibility of anticipating extreme events and reliably detecting their catastrophic effects afterwards. However, these efforts are rarely linked to one another and there is a critical lack of datasets and benchmarks to enable the direct forecasting of flood extent. To resolve this issue, we curate a novel dataset enabling a timely prediction of flood extent. Furthermore, we provide a representative evaluation of state-of-the-art methods, structured into two benchmark tracks for forecasting flood inundation maps i) in general and ii) focused on coastal regions. Altogether, our dataset and benchmark provide a comprehensive platform for evaluating flood forecasts, enabling future solutions for this critical challenge. Data, code & models are shared at https://github.com/Multihuntr/GFF under a CC0 license.

Kai-Hendrik Cohrs, Zuzanna Osika, Maria Gonzalez-Calabuig et al.

Geospatial foundation models for Earth observation often fail to perform reliably in environments underrepresented during pretraining. We introduce SHRUG-FM, a framework for reliability-aware prediction that integrates three complementary signals: out-of-distribution (OOD) detection in the input space, OOD detection in the embedding space and task-specific predictive uncertainty. Applied to burn scar segmentation, SHRUG-FM shows that OOD scores correlate with lower performance in specific environmental conditions, while uncertainty-based flags help discard many poorly performing predictions. Linking these flags to land cover attributes from HydroATLAS shows that failures are not random but concentrated in certain geographies, such as low-elevation zones and large river areas, likely due to underrepresentation in pretraining data. SHRUG-FM provides a pathway toward safer and more interpretable deployment of GFMs in climate-sensitive applications, helping bridge the gap between benchmark performance and real-world reliability.

Patrick Ebel, Michał Patryk Miazga, Martin Lorenz et al.

Designing and evaluating in-vehicle interfaces requires experimental platforms that combine ecological validity with experimental control. Driving simulators are widely used for this purpose. However, they face a fundamental trade-off: high-fidelity physical simulators are costly and difficult to adapt, while virtual reality simulators provide flexibility at the expense of physical interaction with the vehicle. In this work, we present MRDrive, an open mixed-reality driving simulator designed to support HCI research on in-vehicle interaction, attention, and explainability in manual and automated driving contexts. MRDrive enables drivers and passengers to interact with a real vehicle cabin while being fully immersed in a virtual driving environment. We demonstrate the capabilities of MRDrive through a small pilot study that illustrates how the simulator can be used to collect and analyze eye-tracking and touch interaction data in an automated driving scenario. MRDRive is available at: https://github.com/ciao-group/mrdrive

Simon Lämmer, Mark Colley, Patrick Ebel

People's transportation choices reflect complex trade-offs shaped by personal preferences, social norms, and technology acceptance. Predicting such behavior at scale is a critical challenge with major implications for urban planning and sustainable transport. Traditional methods use handcrafted assumptions and costly data collection, making them impractical for early-stage evaluations of new technologies or policies. We introduce Generative Traffic Agents (GTA) for simulating large-scale, context-sensitive transportation choices using LLM-powered, persona-based agents. GTA generates artificial populations from census-based sociodemographic data. It simulates activity schedules and mode choices, enabling scalable, human-like simulations without handcrafted rules. We evaluate GTA in Berlin-scale experiments, comparing simulation results against empirical data. While agents replicate patterns, such as modal split by socioeconomic status, they show systematic biases in trip length and mode preference. GTA offers new opportunities for modeling how future innovations, from bike lanes to transit apps, shape mobility decisions.

Martin Lorenz, Niko Konzack, Alexander Lingler et al.

Designing mobile and interactive technologies requires understanding how users sample dynamic environments to acquire information and make decisions under time pressure. However, existing computational user models either rely on hand-crafted task representations or are limited to static or non-interactive visual inputs, restricting their applicability to realistic, pixel-based environments. We present CR-Eyes, a computationally rational model that simulates visual sampling and gameplay behavior in Atari games. Trained via reinforcement learning, CR-Eyes operates under perceptual and cognitive constraints and jointly learns where to look and how to act in a time-sensitive setting. By explicitly closing the perception-action loop, the model treats eye movements as goal-directed actions rather than as isolated saliency predictions. Our evaluation shows strong alignment with human data in task performance and aggregate saliency patterns, while also revealing systematic differences in scanpaths. CR-Eyes is a step toward scalable, theory-grounded user models that support design and evaluation of interactive systems.

Michał Patryk Miazga, Patrick Ebel

Biomechanical forward simulation holds great potential for HCI, enabling the generation of human-like movements in interactive tasks. However, training biomechanical models with reinforcement learning is challenging, particularly for precise and dexterous movements like those required for touchscreen interactions on mobile devices. Current approaches are limited in their interaction fidelity, require restricting the underlying biomechanical model to reduce complexity, and do not generalize well. In this work, we propose practical improvements to training routines that reduce training time, increase interaction fidelity beyond existing methods, and enable the use of more complex biomechanical models. Using a touchscreen pointing task, we demonstrate that curriculum learning, action masking, more complex network configurations, and simple adjustments to the simulation environment can significantly improve the agent's ability to learn accurate touch behavior. Our work provides HCI researchers with practical tips and training routines for developing better biomechanical models of human-like interaction fidelity.

Jussi Jokinen, Patrick Ebel, Tuomo Kujala

Modern driving involves interactive technologies that can divert attention, increasing the risk of accidents. This paper presents a computational cognitive model that simulates human multitasking while driving. Based on optimal supervisory control theory, the model predicts how multitasking adapts to variations in driving demands, interactive tasks, and automation levels. Unlike previous models, it accounts for context-dependent multitasking across different degrees of driving automation. The model predicts longer in-car glances on straight roads and shorter glances during curves. It also anticipates increased glance durations with driver aids such as lane-centering assistance and their interaction with environmental demands. Validated against two empirical datasets, the model offers insights into driver multitasking amid evolving in-car technologies and automation.

Michał Patryk Miazga, Hannah Bussmann, Antti Oulasvirta et al.

Touch data from mobile devices are collected at scale but reveal little about the interactions that produce them. While biomechanical simulations can illuminate motor control processes, they have not yet been developed for touch interactions. To close this gap, we propose a novel computational problem: synthesizing plausible motion directly from logs. Our key insight is a reinforcement learning-driven musculoskeletal forward simulation that generates biomechanically plausible motion sequences consistent with events recorded in touch logs. We achieve this by integrating a software emulator into a physics simulator, allowing biomechanical models to manipulate real applications in real-time. Log2Motion produces rich syntheses of user movements from touch logs, including estimates of motion, speed, accuracy, and effort. We assess the plausibility of generated movements by comparing against human data from a motion capture study and prior findings, and demonstrate Log2Motion in a large-scale dataset. Biomechanical motion synthesis provides a new way to understand log data, illuminating the ergonomics and motor control underlying touch interactions.

Patrick Ebel, Brandon Victor, Peter Naylor et al.

Hurricanes and coastal floods are among the most disastrous natural hazards. Both are intimately related to storm surges, as their causes and effects, respectively. However, the short-term forecasting of storm surges has proven challenging, especially when targeting previously unseen locations or sites without tidal gauges. Furthermore, recent work improved short and medium-term weather forecasting but the handling of raw unassimilated data remains non-trivial. In this paper, we tackle both challenges and demonstrate that neural networks can implicitly assimilate sparse in situ tide gauge data with coarse ocean state reanalysis in order to forecast storm surges. We curate a global dataset to learn and validate the dense prediction of storm surges, building on preceding efforts. Other than prior work limited to known gauges, our approach extends to ungauged sites, paving the way for global storm surge forecasting.

Patrick Ebel, Yajin Xu, Michael Schmitt et al.

About half of all optical observations collected via spaceborne satellites are affected by haze or clouds. Consequently, cloud coverage affects the remote sensing practitioner's capabilities of a continuous and seamless monitoring of our planet. This work addresses the challenge of optical satellite image reconstruction and cloud removal by proposing a novel multi-modal and multi-temporal data set called SEN12MS-CR-TS. We propose two models highlighting the benefits and use cases of SEN12MS-CR-TS: First, a multi-modal multi-temporal 3D-Convolution Neural Network that predicts a cloud-free image from a sequence of cloudy optical and radar images. Second, a sequence-to-sequence translation model that predicts a cloud-free time series from a cloud-covered time series. Both approaches are evaluated experimentally, with their respective models trained and tested on SEN12MS-CR-TS. The conducted experiments highlight the contribution of our data set to the remote sensing community as well as the benefits of multi-modal and multi-temporal information to reconstruct noisy information. Our data set is available at https://patrickTUM.github.io/cloud_removal

Patrick Ebel, Christoph Lingenfelder, Andreas Vogelsang

Center touchscreens are the main HMI (Human-Machine Interface) between the driver and the vehicle. They are becoming, larger, increasingly complex and replace functions that could previously be controlled using haptic interfaces. To ensure that touchscreen HMI can be operated safely, they are subject to strict regulations and elaborate test protocols. Those methods and user trials require fully functional prototypes and are expensive and time-consuming. Therefore it is desirable to estimate the workload of specific interfaces or interaction sequences as early as possible in the development process. To address this problem, we envision a model-based approach that, based on the combination of user interactions and UI elements, can predict the secondary task load of the driver when interacting with the center screen. In this work, we present our current status, preliminary results, and our vision for a model-based system build upon large-scale natural driving data.

Patrick Ebel, Christoph Lingenfelder, Andreas Vogelsang

With modern IVIS becoming more capable and complex than ever, their evaluation becomes increasingly difficult. The analysis of large amounts of user behavior data can help to cope with this complexity and can support UX experts in designing IVIS that serve customer needs and are safe to operate while driving. We, therefore, propose a Multi-level User Behavior Visualization Framework providing effective visualizations of user behavior data that is collected via telematics from production vehicles. Our approach visualizes user behavior data on three different levels: (1) The Task Level View aggregates event sequence data generated through touchscreen interactions to visualize user flows. (2) The Flow Level View allows comparing the individual flows based on a chosen metric. (3) The Sequence Level View provides detailed insights into touch interactions, glance, and driving behavior. Our case study proves that UX experts consider our approach a useful addition to their design process.

Sudipan Saha, Patrick Ebel, Xiao Xiang Zhu

Most change detection methods assume that pre-change and post-change images are acquired by the same sensor. However, in many real-life scenarios, e.g., natural disaster, it is more practical to use the latest available images before and after the occurrence of incidence, which may be acquired using different sensors. In particular, we are interested in the combination of the images acquired by optical and Synthetic Aperture Radar (SAR) sensors. SAR images appear vastly different from the optical images even when capturing the same scene. Adding to this, change detection methods are often constrained to use only target image-pair, no labeled data, and no additional unlabeled data. Such constraints limit the scope of traditional supervised machine learning and unsupervised generative approaches for multi-sensor change detection. Recent rapid development of self-supervised learning methods has shown that some of them can even work with only few images. Motivated by this, in this work we propose a method for multi-sensor change detection using only the unlabeled target bi-temporal images that are used for training a network in self-supervised fashion by using deep clustering and contrastive learning. The proposed method is evaluated on four multi-modal bi-temporal scenes showing change and the benefits of our self-supervised approach are demonstrated.

Patrick Ebel, Andrea Meraner, Michael Schmitt et al.

This work has been accepted by IEEE TGRS for publication. The majority of optical observations acquired via spaceborne earth imagery are affected by clouds. While there is numerous prior work on reconstructing cloud-covered information, previous studies are oftentimes confined to narrowly-defined regions of interest, raising the question of whether an approach can generalize to a diverse set of observations acquired at variable cloud coverage or in different regions and seasons. We target the challenge of generalization by curating a large novel data set for training new cloud removal approaches and evaluate on two recently proposed performance metrics of image quality and diversity. Our data set is the first publically available to contain a global sample of co-registered radar and optical observations, cloudy as well as cloud-free. Based on the observation that cloud coverage varies widely between clear skies and absolute coverage, we propose a novel model that can deal with either extremes and evaluate its performance on our proposed data set. Finally, we demonstrate the superiority of training models on real over synthetic data, underlining the need for a carefully curated data set of real observations. To facilitate future research, our data set is made available online

Patrick Ebel, Florian Brokhausen, Andreas Vogelsang

We are interested in the role of field user interaction data in the development of IVIS, the potentials practitioners see in analyzing this data, the concerns they share, and how this compares to companies with digital products. We conducted interviews with 14 UX professionals, 8 from automotive and 6 from digital companies, and analyzed the results by emergent thematic coding. Our key findings indicate that implicit feedback through field user interaction data is currently not evident in the automotive UX development process. Most decisions regarding the design of IVIS are made based on personal preferences and the intuitions of stakeholders. However, the interviewees also indicated that user interaction data has the potential to lower the influence of guesswork and assumptions in the UX design process and can help to make the UX development lifecycle more evidence-based and user-centered.

Kim Julian Gülle, Nicholas Ford, Patrick Ebel et al.

Requirements elicitation has recently been complemented with crowd-based techniques, which continuously involve large, heterogeneous groups of users who express their feedback through a variety of media. Crowd-based elicitation has great potential for engaging with (potential) users early on but also results in large sets of raw and unstructured feedback. Consolidating and analyzing this feedback is a key challenge for turning it into sensible user requirements. In this paper, we focus on topic modeling as a means to identify topics within a large set of crowd-generated user stories and compare three approaches: (1) a traditional approach based on Latent Dirichlet Allocation, (2) a combination of word embeddings and principal component analysis, and (3) a combination of word embeddings and Word Mover's Distance. We evaluate the approaches on a publicly available set of 2,966 user stories written and categorized by crowd workers. We found that a combination of word embeddings and Word Mover's Distance is most promising. Depending on the word embeddings we use in our approaches, we manage to cluster the user stories in two ways: one that is closer to the original categorization and another that allows new insights into the dataset, e.g. to find potentially new categories. Unfortunately, no measure exists to rate the quality of our results objectively. Still, our findings provide a basis for future work towards analyzing crowd-sourced user stories.

Patrick Ebel, Ibrahim Emre Göl, Christoph Lingenfelder et al.

Two-thirds of the people who buy a new car prefer to use a substitute instead of the built-in navigation system. However, for many applications, knowledge about a user's intended destination and route is crucial. For example, suggestions for available parking spots close to the destination can be made or ride-sharing opportunities along the route are facilitated. Our approach predicts probable destinations and routes of a vehicle, based on the most recent partial trajectory and additional contextual data. The approach follows a three-step procedure: First, a $k$-d tree-based space discretization is performed, mapping GPS locations to discrete regions. Secondly, a recurrent neural network is trained to predict the destination based on partial sequences of trajectories. The neural network produces destination scores, signifying the probability of each region being the destination. Finally, the routes to the most probable destinations are calculated. To evaluate the method, we compare multiple neural architectures and present the experimental results of the destination prediction. The experiments are based on two public datasets of non-personalized, timestamped GPS locations of taxi trips. The best performing models were able to predict the destination of a vehicle with a mean error of 1.3 km and 1.43 km respectively.

Michael Schmitt, Jonathan Prexl, Patrick Ebel et al.

Fully automatic large-scale land cover mapping belongs to the core challenges addressed by the remote sensing community. Usually, the basis of this task is formed by (supervised) machine learning models. However, in spite of recent growth in the availability of satellite observations, accurate training data remains comparably scarce. On the other hand, numerous global land cover products exist and can be accessed often free-of-charge. Unfortunately, these maps are typically of a much lower resolution than modern day satellite imagery. Besides, they always come with a significant amount of noise, as they cannot be considered ground truth, but are products of previous (semi-)automatic prediction tasks. Therefore, this paper seeks to make a case for the application of weakly supervised learning strategies to get the most out of available data sources and achieve progress in high-resolution large-scale land cover mapping. Challenges and opportunities are discussed based on the SEN12MS dataset, for which also some baseline results are shown. These baselines indicate that there is still a lot of potential for dedicated approaches designed to deal with remote sensing-specific forms of weak supervision.

Patrick Ebel, Anastasiia Mishchuk, Kwang Moo Yi et al.

The dominant approach for learning local patch descriptors relies on small image regions whose scale must be properly estimated a priori by a keypoint detector. In other words, if two patches are not in correspondence, their descriptors will not match. A strategy often used to alleviate this problem is to "pool" the pixel-wise features over log-polar regions, rather than regularly spaced ones. By contrast, we propose to extract the "support region" directly with a log-polar sampling scheme. We show that this provides us with a better representation by simultaneously oversampling the immediate neighbourhood of the point and undersampling regions far away from it. We demonstrate that this representation is particularly amenable to learning descriptors with deep networks. Our models can match descriptors across a much wider range of scales than was possible before, and also leverage much larger support regions without suffering from occlusions. We report state-of-the-art results on three different datasets.