arXiv subjects

Ulrich Schwanecke

Publications and source records attributed to Ulrich Schwanecke.

17 recordsLinked to original sources

arXiv2026

Speak to the City: Multimodal Resolution for Outside-the-Vehicle References

As autonomous vehicles and Extended Reality (XR) headsets enable novel in-car interactions, seamlessly querying physical landmarks, known as Outside-the-Vehicle Referencing (OVR), remains challenging due to ego-motion and referential ambiguity. We present a robust, multimodal OVR framework fusing user gaze and natural language to identify Points of Interest (POIs). To address the scarcity of dynamic vehicular data, we developed a VR-based pipeline synchronizing 360-degree transit videos with vehicle GNSS telemetry. Through a user study (N=46) mapping passenger head orientation into a 3D geospatial Digital Twin, we captured authentic gaze-speech behaviors. We subsequently trained a lightweight Transformer network, leveraging LLMs to dynamically align continuous spatial gaze vectors with discrete verbal context. Experimental results demonstrate high accuracy and low computational overhead, achieving an 83.33% Top-1 accuracy (87.72% Top-2) and an average inference time of 24.3 milliseconds. This real-time paradigm effectively resolves referential ambiguity, enabling context-aware spatial retrieval for passengers within the vehicle.

cs.HC↗

arXiv2026

DocDjinn: Controllable Synthetic Document Generation with VLMs and Handwriting Diffusion

Effective document intelligence models rely on large amounts of annotated training data. However, procuring sufficient and high-quality data poses significant challenges due to the labor-intensive and costly nature of data acquisition. Additionally, leveraging language models to annotate real documents raises concerns about data privacy. Synthetic document generation has emerged as a promising, privacy-preserving alternative. We propose DocDjinn, a novel framework for controllable synthetic document generation using Vision-Language Models (VLMs) that produces annotated documents from unlabeled seed samples. Our approach generates visually plausible and semantically consistent synthetic documents that follow the distribution of an existing source dataset through clustering-based seed selection with parametrized sampling. By enriching documents with realistic diffusion-based handwriting and contextual visual elements via semantic-visual decoupling, we generate diverse, high-quality annotated synthetic documents. We evaluate across eleven benchmarks spanning key information extraction, question answering, document classification, and document layout analysis. To our knowledge, this is the first work demonstrating that VLMs can generate faithful annotated document datasets at scale from unlabeled seeds that can effectively enrich or approximate real, manually annotated data for diverse document understanding tasks. We show that with only 100 real training samples, our framework achieves on average $87\%$ of the performance of the full real-world dataset. We publicly release our code and 140k+ synthetic document samples.

cs.LG↗

arXiv2025

Blending the Worlds: World-Fixed Visual Appearances in Automotive Augmented Reality

With the transition to fully autonomous vehicles, non-driving related tasks (NDRTs) become increasingly important, allowing passengers to use their driving time more efficiently. In-car Augmented Reality (AR) gives the possibility to engage in NDRTs while also allowing passengers to engage with their surroundings, for example, by displaying world-fixed points of interest (POIs). This can lead to new discoveries, provide information about the environment, and improve locational awareness. To explore the optimal visualization of POIs using in-car AR, we conducted a field study (N = 38) examining six parameters: positioning, scaling, rotation, render distance, information density, and appearance. We also asked for intention of use, preferred seat positions and preferred automation level for the AR function in a post-study questionnaire. Our findings reveal user preferences and general acceptance of the AR functionality. Based on these results, we derived UX-guidelines for the visual appearance and behavior of location-based POIs in in-car AR.

cs.HC↗

arXiv2025

Augmented Journeys: Interactive Points of Interest for In-Car Augmented Reality

As passengers spend more time in vehicles, the demand for non-driving related tasks (NDRTs) increases. In-car Augmented Reality (AR) has the potential to enhance passenger experiences by enabling interaction with the environment through NDRTs using world-fixed Points of Interest (POIs). However, the effectiveness of existing interaction techniques and visualization methods for in-car AR remains unclear. Based on a survey (N=110) and a pre-study (N=10), we developed an interactive in-car AR system using a video see-through head-mounted display to engage with POIs via eye-gaze and pinch. Users could explore passed and upcoming POIs using three visualization techniques: List, Timeline, and Minimap. We evaluated the system's feasibility in a field study (N=21). Our findings indicate general acceptance of the system, with the List visualization being the preferred method for exploring POIs. Additionally, the study highlights limitations of current AR hardware, particularly the impact of vehicle movement on 3D interaction.

cs.HC↗

arXiv2024

NePHIM: A Neural Physics-Based Head-Hand Interaction Model

Due to the increasing use of virtual avatars, the animation of head-hand interactions has recently gained attention. To this end, we present a novel volumetric and physics-based interaction simulation. In contrast to previous work, our simulation incorporates temporal effects such as collision paths, respects anatomical constraints, and can detect and simulate skin pulling. As a result, we can achieve more natural-looking interaction animations and take a step towards greater realism. However, like most complex and computationally expensive simulations, ours is not real-time capable even on high-end machines. Therefore, we train small and efficient neural networks as accurate approximations that achieve about 200 FPS on consumer GPUs, about 50 FPS on CPUs, and are learned in less than four hours for one person. In general, our focus is not to generalize the approximation networks to low-resolution head models but to adapt them to more detailed personalized avatars. Nevertheless, we show that these networks can learn to approximate our head-hand interaction model for multiple identities while maintaining computational efficiency. Since the quality of the simulations can only be judged subjectively, we conducted a comprehensive user study which confirms the improved realism of our approach. In addition, we provide extensive visual results and inspect the neural approximations quantitatively. All data used in this work has been recorded with a multi--view camera rig and will be made available upon publication. We will also publish relevant implementations.

cs.GR↗

arXiv2023

Vocalics in Human-Drone Interaction

As the presence of flying robots continues to grow in both commercial and private sectors, it necessitates an understanding of appropriate methods for nonverbal interaction with humans. While visual cues, such as gestures incorporated into trajectories, are more apparent and thoroughly researched, acoustic cues have remained unexplored, despite their potential to enhance human-drone interaction. Given that additional audiovisual and sensory equipment is not always desired or practicable, and flight noise often masks potential acoustic communication in rotary-wing drones, such as through a loudspeaker, the rotors themselves offer potential for nonverbal communication. In this paper, quadrotor trajectories are augmented by acoustic information that does not visually affect the flight, but adds audible information that significantly facilitates distinctiveness. A user study (N=192) demonstrates that sonically augmenting the trajectories of two aerial gestures makes them more easily distinguishable. This enhancement contributes to human-drone interaction through onboard means, particularly in situations where the human cannot see or look at the drone.

cs.RO↗

arXiv2023

TailorMe: Self-Supervised Learning of an Anatomically Constrained Volumetric Human Shape Model

Human shape spaces have been extensively studied, as they are a core element of human shape and pose inference tasks. Classic methods for creating a human shape model register a surface template mesh to a database of 3D scans and use dimensionality reduction techniques, such as Principal Component Analysis, to learn a compact representation. While these shape models enable global shape modifications by correlating anthropometric measurements with the learned subspace, they only provide limited localized shape control. We instead register a volumetric anatomical template, consisting of skeleton bones and soft tissue, to the surface scans of the CAESAR database. We further enlarge our training data to the full Cartesian product of all skeletons and all soft tissues using physically plausible volumetric deformation transfer. This data is then used to learn an anatomically constrained volumetric human shape model in a self-supervised fashion. The resulting TailorMe model enables shape sampling, localized shape manipulation, and fast inference from given surface scans.

cs.CV↗

arXiv2023

LEAVEN -- Lightweight Surface and Volume Mesh Sampling Application for Particle-based Simulations

We present an easy-to-use and lightweight surface and volume mesh sampling standalone application tailored for the needs of particle-based simulation. We describe the surface and volume sampling algorithms used in LEAVEN in a beginner-friendly fashion. Furthermore, we describe a novel method of generating random volume samples that satisfy blue noise criteria by modifying a surface sampling algorithm. We aim to lower one entry barrier for starting with particle-based simulations while still pose a benefit to advanced users. The goal is to provide a useful tool to the community and lowering the need for heavyweight third-party applications, especially for starters.

cs.GR↗

arXiv2023

Interactive High-Resolution Simulation of Granular Material

We introduce a particle-based simulation method for granular material in interactive frame rates. We divide the simulation into two decoupled steps. In the first step, a relatively small number of particles is accurately simulated with a constraint-based method. Here, all collisions and the resulting friction between the particles are taken into account. In the second step, the small number of particles is significantly increased by an efficient sampling algorithm without creating additional artifacts. The method is particularly robust and allows relatively large time steps, which makes it well suited for real-time applications. With our method, up to 500k particles can be computed in interactive frame rates on consumer CPUs without relying on GPU support for massive parallel computing. This makes it well suited for applications where a lot of GPU power is already needed for render tasks.

cs.GR↗

arXiv2023

Real-time Light Estimation and Neural Soft Shadows for AR Indoor Scenarios

We present a pipeline for realistic embedding of virtual objects into footage of indoor scenes with focus on real-time AR applications. Our pipeline consists of two main components: A light estimator and a neural soft shadow texture generator. Our light estimation is based on deep neural nets and determines the main light direction, light color, ambient color and an opacity parameter for the shadow texture. Our neural soft shadow method encodes object-based realistic soft shadows as light direction dependent textures in a small MLP. We show that our pipeline can be used to integrate objects into AR scenes in a new level of realism in real-time. Our models are small enough to run on current mobile devices. We achieve runtimes of 9ms for light estimation and 5ms for neural shadows on an iPhone 11 Pro.

cs.CV↗

arXiv2023

Assessing Augmented Reality Selection Techniques for Passengers in Moving Vehicles: A Real-World User Study

Nowadays, cars offer many possibilities to explore the world around you by providing location-based information displayed on a 2D-Map. However, this information is often only available to front-seat passengers while being restricted to in-car displays. To propose a more natural way of interacting with the environment, we implemented an augmented reality head-mounted display to overlay points of interest onto the real world. We aim to compare multiple selection techniques for digital objects located outside a moving car by investigating head gaze with dwell time, head gaze with hardware button, eye gaze with hardware button, and hand pointing with gesture confirmation. Our study was conducted in a moving car under real-world conditions (N=22), with significant results indicating that hand pointing usage led to slower and less precise content selection while eye gaze was preferred by participants and performed on par with the other techniques.

cs.HC↗

arXiv2023

Neural Volumetric Blendshapes: Computationally Efficient Physics-Based Facial Blendshapes

Computationally weak systems and demanding graphical applications are still mostly dependent on linear blendshapes for facial animations. The accompanying artifacts such as self-intersections, loss of volume, or missing soft tissue elasticity can be avoided by using physics-based animation models. However, these are cumbersome to implement and require immense computational effort. We propose neural volumetric blendshapes, an approach that combines the advantages of physics-based simulations with realtime runtimes even on consumer-grade CPUs. To this end, we present a neural network that efficiently approximates the involved volumetric simulations and generalizes across human identities as well as facial expressions. Our approach can be used on top of any linear blendshape system and, hence, can be deployed straightforwardly. Furthermore, it only requires a single neutral face mesh as input in the minimal setting. Along with the design of the network, we introduce a pipeline for the challenging creation of anatomically and physically plausible training data. Part of the pipeline is a novel hybrid regressor that densely positions a skull within a skin surface while avoiding intersections. The fidelity of all parts of the data generation pipeline as well as the accuracy and efficiency of the network are evaluated in this work. Upon publication, the trained models and associated code will be released.

cs.GR↗

arXiv2022

Addressing Leakage in Self-Supervised Contextualized Code Retrieval

We address contextualized code retrieval, the search for code snippets helpful to fill gaps in a partial input program. Our approach facilitates a large-scale self-supervised contrastive training by splitting source code randomly into contexts and targets. To combat leakage between the two, we suggest a novel approach based on mutual identifier masking, dedentation, and the selection of syntax-aligned targets. Our second contribution is a new dataset for direct evaluation of contextualized code retrieval, based on a dataset of manually aligned subpassages of code clones. Our experiments demonstrate that our approach improves retrieval substantially, and yields new state-of-the-art results for code clone and defect detection.

cs.SE↗

arXiv2020

NeuralQAAD: An Efficient Differentiable Framework for High Resolution Point Cloud Compression

In this paper, we propose NeuralQAAD, a differentiable point cloud compression framework that is fast, robust to sampling, and applicable to high resolutions. Previous work that is able to handle complex and non-smooth topologies is hardly scaleable to more than just a few thousand points. We tackle the task with a novel neural network architecture characterized by weight sharing and autodecoding. Our architecture uses parameters much more efficiently than previous work, allowing us to be deeper and scalable. Futhermore, we show that the currently only tractable training criterion for point cloud compression, the Chamfer distance, performances poorly for high resolutions. To overcome this issue, we pair our architecture with a new training procedure based upon a quadratic assignment problem (QAP) for which we state two approximation algorithms. We solve the QAP in parallel to gradient descent. This procedure acts as a surrogate loss and allows to implicitly minimize the more expressive Earth Movers Distance (EMD) even for point clouds with way more than $10^6$ points. As evaluating the EMD on high resolution point clouds is intractable, we propose a divide-and-conquer approach based on k-d trees, the EM-kD, as a scaleable and fast but still reliable upper bound for the EMD. NeuralQAAD is demonstrated on COMA, D-FAUST, and Skulls to significantly outperform the current state-of-the-art visually and in terms of the EM-kD. Skulls is a novel dataset of skull CT-scans which we will make publicly available together with our implementation of NeuralQAAD.

cs.CV↗

arXiv2019

An Open-World Extension to Knowledge Graph Completion Models

We present a novel extension to embedding-based knowledge graph completion models which enables them to perform open-world link prediction, i.e. to predict facts for entities unseen in training based on their textual description. Our model combines a regular link prediction model learned from a knowledge graph with word embeddings learned from a textual corpus. After training both independently, we learn a transformation to map the embeddings of an entity's name and description to the graph-based embedding space. In experiments on several datasets including FB20k, DBPedia50k and our new dataset FB15k-237-OWE, we demonstrate competitive results. Particularly, our approach exploits the full knowledge graph structure even when textual descriptions are scarce, does not require a joint training on graph and text, and can be applied to any embedding-based link prediction model, such as TransE, ComplEx and DistMult.

cs.AI↗

arXiv2018

A Region-based Gauss-Newton Approach to Real-Time Monocular Multiple Object Tracking

We propose an algorithm for real-time 6DOF pose tracking of rigid 3D objects using a monocular RGB camera. The key idea is to derive a region-based cost function using temporally consistent local color histograms. While such region-based cost functions are commonly optimized using first-order gradient descent techniques, we systematically derive a Gauss-Newton optimization scheme which gives rise to drastically faster convergence and highly accurate and robust tracking performance. We furthermore propose a novel complex dataset dedicated for the task of monocular object pose tracking and make it publicly available to the community. To our knowledge, it is the first to address the common and important scenario in which both the camera as well as the objects are moving simultaneously in cluttered scenes. In numerous experiments - including our own proposed dataset - we demonstrate that the proposed Gauss-Newton approach outperforms existing approaches, in particular in the presence of cluttered backgrounds, heterogeneous objects and partial occlusions.

cs.CV↗

arXiv2018

A method for automatic forensic facial reconstruction based on dense statistics of soft tissue thickness

In this paper, we present a method for automated estimation of a human face given a skull remain. The proposed method is based on three statistical models. A volumetric (tetrahedral) skull model encoding the variations of different skulls, a surface head model encoding the head variations, and a dense statistic of facial soft tissue thickness (FSTT). All data are automatically derived from computed tomography (CT) head scans and optical face scans. In order to obtain a proper dense FSTT statistic, we register a skull model to each skull extracted from a CT scan and determine the FSTT value for each vertex of the skull model towards the associated extracted skin surface. The FSTT values at predefined landmarks from our statistic are well in agreement with data from the literature. To recover a face from a skull remain, we first fit our skull model to the given skull. Next, we generate spheres with radius of the respective FSTT value obtained from our statistic at each vertex of the registered skull. Finally, we fit a head model to the union of all spheres. The proposed automated method enables a probabilistic face-estimation that facilitates forensic recovery even from incomplete skull remains. The FSTT statistic allows the generation of plausible head variants, which can be adjusted intuitively using principal component analysis. We validate our face recovery process using an anonymized head CT scan. The estimation generated from the given skull visually compares well with the skin surface extracted from the CT scan itself.

cs.CV↗