VMV2025

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/3607231

Browse

Now showing 1 - 20 of 22

Alias-Free Shadows with Ray Cones for Alpha Tested Geometry
(The Eurographics Association, 2025) Brüll, Felix; Kern, René; Grosch, Thorsten; Egger, Bernhard; Günther, Tobias
We present a method for computing alias-free, smooth shadows for alpha-tested geometry using a single ray per pixel. Without mipmap filtering, hard shadows from alpha-tested geometry appear very noisy under camera motion. Typically, many ray samples are required to soften the shadows and reduce noise. We propose using mipmaps instead, to achieve a fast and temporally stable solution. To determine the appropriate mipmap level, we introduce novel ray cone operations that account for directional and point light sources.
A Bag of Tricks for Efficient Implicit Neural Point Clouds
(The Eurographics Association, 2025) Hahlbohm, Florian; Franke, Linus; Overkämping, Leon; Wespe, Paula; Castillo, Susana; Eisemann, Martin; Magnor, Marcus; Egger, Bernhard; Günther, Tobias
Implicit Neural Point Cloud (INPC) is a recent hybrid representation that combines the expressiveness of neural fields with the efficiency of point-based rendering, achieving state-of-the-art image quality in novel view synthesis. However, as with other high-quality approaches that query neural networks during rendering, the practical usability of INPC is limited by comparatively slow rendering. In this work, we present a collection of optimizations that significantly improve both the training and inference performance of INPC without sacrificing visual fidelity. The most significant modifications are an improved rasterizer implementation, more effective sampling techniques, and the incorporation of pre-training for the convolutional neural network used for hole-filling. Furthermore, we demonstrate that points can be modeled as small Gaussians during inference to further improve quality in extrapolated, e.g., close-up views of the scene. We design our implementations to be broadly applicable beyond INPC and systematically evaluate each modification in a series of experiments. Our optimized INPC pipeline achieves up to 25% faster training, 2× faster rendering, and 20% reduced VRAM usage paired with slight image quality improvements.
Bijective Feature-Aware Contour Matching
(The Eurographics Association, 2025) Selman, Zain; Speetzen, Nils; Kobbelt, Leif; Egger, Bernhard; Günther, Tobias
Computing maps between data sequences is a fundamental problem with various applications in the fields of geometry and signal processing. As such, a multitude of approaches exist, that make trade-offs between flexibility, performance, and accuracy. Even recent approaches cannot be applied to periodic data, such as contours, without significant compromises due to their map representation or method of optimization. We propose a universal method to optimize maps between periodic and non periodic univariate sequences. By continuously optimizing a piecewise linear approximation of the smooth map on a common intermediate domain, we decouple the map and input resolution. Our optimization offers bijectivity guarantees and flexibility with regards to applications and data modality. To robustly converge towards a high quality solution we initially apply a lowpass filter to the input. This creates a scale space that suppresses local features in the early phase of the optimization (global phase) and gradually adds them back later (local phase). We demonstrate the versatility of our method on various scenarios with different types of sequences, including multi-contour morphing, signature prototypes, symmetry detection, and 3D motioncapture- data alignment.
Bin-VBSR: Variable Block Size Binned Block-Compressed Sparse Row for Efficient GPU-Accelerated Finite Element Analysis
(The Eurographics Association, 2025) Pfeil, Florian; Ferreira, Stephanie; Mueller-Roemer, Johannes Sebastian; Egger, Bernhard; Günther, Tobias
We present Binned Variable Block Compressed Sparse Row (Bin-VBSR), a novel GPU-optimized sparse matrix data structure and associated sparse matrix-vector multiplication algorithm for matrices with variable-size dense blocks. This includes a novel approach to handling long rows in the Binned Compressed Sparse Row (Bin-CSR) family of GPU-optimized sparse matrix data structures. We demonstrate speedups of up to 9.9× over Bin-BCSR* and extend its data compression advantages over compressed sparse row (CSR) to variable block size, resulting in an improvement of up to 50%.
CharGen: Fast and Fluent Portrait Modification
(The Eurographics Association, 2025) Dihlmann, Jan-Niklas; Killguss, Arnela; Lensch, Hendrik; Egger, Bernhard; Günther, Tobias
Interactive editing of character images with diffusion models remains challenging due to the inherent trade-off between fine-grained control, generation speed, and visual fidelity. We introduce CharGen, a character-focused editor that combines attribute-specific Concept Sliders, trained to isolate and manipulate attributes such as facial feature size, expression, and decoration with the StreamDiffusion sampling pipeline for more interactive performance. To counteract the loss of detail that often accompanies accelerated sampling, we propose a lightweight Repair Step that reinstates fine textures without compromising structural consistency. Throughout extensive ablation studies and in comparison to open-source InstructPix2Pix and closedsource Google Gemini, and a comprehensive user study, CharGen achieves two-to-four-fold faster edit turnaround with precise editing control and identity-consistent results. Project page: https://chargen.jdihlmann.com/
Differentiable XPBD for Gradient-Based Learning of Physical Parameters from Motion
(The Eurographics Association, 2025) Drysch, Simone; Stotko, David; Klein, Reinhard; Egger, Bernhard; Günther, Tobias
Accurate cloth simulation is a vital component in computer graphics, virtual reality, and fashion design. Position-Based Dynamics (PBD) and its extension (XPBD) offer robust and efficient methods for simulating deformable objects like cloth. This paper details the evaluation and comparison of cloth simulations based on XPBD, including its ''small steps'' variant and an Energy- Aware (EA) modification. The XPBD variants are evaluated for their physical plausibility and energy conservation to analyze their suitability for inverse problems. Furthermore, we explore the implementation of a differentiable XPBD simulator, enabling the estimation of material properties and external forces. The differentiable simulator is assessed for its capability to estimate parameters in scenarios of increasing complexity. Results indicate that small time steps with single iterations in XPBD offer good energy behavior, while the EA modification exhibits undesired characteristics. The differentiable simulator successfully estimates single parameters but identifies challenges with multi-parameter optimization due to compensatory effects.
Exploring the Geometry of Swarm Intelligence: Negative Inertia and Ellipsoidal Search Space Evolution in PSO
(The Eurographics Association, 2025) Krämer, Katharina; Müller, Stefan; Kosterhon, Michael; Egger, Bernhard; Günther, Tobias
This paper introduces a geometry-aware method for analyzing swarm behavior in Particle Swarm Optimization (PSO) based on ellipsoidal modeling. Inspired by the n-ball hitting probability, we propose an abstraction of the search space covered by particles over time. Using principal component analysis (PCA), we approximate the particle distribution at each iteration with ellipsoids, enabling a visual and quantitative assessment of how well the swarm explores and concentrates its search effort. We apply this technique to investigate a PSO variant with negative inertia weights, which has shown promising performance in prior empirical analysis. While negative inertia may appear counterintuitive, our ellipsoidal analysis reveals that it introduces oscillatory search dynamics that balance exploration and exploitation more effectively than standard strategies such as constant inertia or linear decreasing inertia. Our experiments include a six-dimensional medical image registration task and an illustrative two-dimensional Rastrigin function, which serves to visually demonstrate how the swarm structure evolves. The proposed analysis framework provides new insight into swarm dynamics and offers a tool for understanding and comparing the behavior of PSO variants beyond conventional performance metrics.
Fast Camera Calibration from Orthographic Views of Rotated Objects
(The Eurographics Association, 2025) Rak, Arne; Wirth, Tristan; Knauthe, Volker; Kuijper, Arjan; Fellner, Dieter W.; Egger, Bernhard; Günther, Tobias
Accurate camera calibration is crucial for high-quality 3D reconstruction in computer vision applications. In industrial measuring scenarios, turntable sequences are often captured using telecentric lenses to overcome the foreshortening effect. While specialized Structure-from-Motion (SfM) solutions exist for orthographic projection, these methods are limited to textured objects. Approaches that leverage the scanned object's silhouette for camera calibration are independent of texture but are often restricted to smooth objects or require non-trivial optimization initializations to converge. In this work, we present a novel silhouette-based approach to estimate the rotation axis of a turntable under orthographic projection, extending the applicability to complex geometries, while requiring little to none parameter adjustments. By identifying the symmetry axis of the object's contour envelope and establishing frontier point correspondences on circular trajectories, we robustly estimate the azimuth and inclination angles of the rotation axis, enabling accurate camera pose computation. We evaluate our approach on synthetic datasets comprising four models with varying characteristics and compare it to a state-of-the-art orthographic SfM method, achieving comparable accuracy, while reducing computational cost 37-fold and eliminating reliance on object texture.
Fast Rendering of Large-Scale Dynamic Multi-Layered Height Maps
(The Eurographics Association, 2025) Nilles, Alexander Maximilian; Müller, Stefan; Egger, Bernhard; Günther, Tobias
In this paper, we develop two methods for fast visualization of fully dynamic large-scale multi-layered height maps (MLHMs). MLHMs are a fairly uncommon data structure in computer graphics, which has been used as an efficient representation of 3D terrain, among other applications. Recently, a 3D hydraulic erosion simulation that utilizes this data structure effectively, allowing for real-time simulation of large scale terrain, was developed, but the fast simulation was paired with slow visualization. We extend this previous work with two efficient visualization methods. Rendering the MLHM as boxes is done using ray tracing, while a smooth surface is rendered by ray marching an implicit surface generated by smoothing the MLHM, following previous work. Both techniques are accelerated using a hierarchical data structure built directly from the MLHM, which enables quadtree-like traversal using 2D DDA, where each 2D cell contains 3D axis-aligned bounding boxes (AABBs). This data structure is adapted to accelerate ray marching by appropriately padding AABBs with the smoothing radius. We further propose a soft shadow method and geometric ambient occlusion that work in tandem with this data structure. Our visualization is fast enough to support fully dynamic terrain in real-time, where simulation, creation of our data structure and visualization are done every single frame in real-time for terrain resolutions up to 40962. For lower resolutions, it is possible to run expensive ray tracing and geometric ambient occlusion effects at full window resolution every frame with real-time or interactive frame rates.
Image Pre-Segmentation from Shadow Masks
(The Eurographics Association, 2025) Heep, Moritz; Parakkat, Amal Dev; Zell, Eduard; Egger, Bernhard; Günther, Tobias
Image segmentation has gained a lot of attention in the past. When working with photometric stereo data, we discovered that shadow cues provide valuable spatial information, especially when combining multiple images of the same scene under different lighting conditions. In the following, we present a robust method to pre-segment images, relying heavily on shadow masks as the main input. We first detect object contours from light to shadow transitions. In the second step, we run an image segmentation algorithm based on Delaunay triangulation that is capable of closing the gaps between contours. Our method requires spatial input data but is free from training data. Initial results look promising, generating pre-segmentations close to recent data-driven image segmentation algorithms.
An Investigation of the Apple Vision Pro for Out-of-Core Ray-Guided Volume Rendering with BorgVR
(The Eurographics Association, 2025) Hrycak, Camilla; Krüger, Jens; Egger, Bernhard; Günther, Tobias
We present an in-depth investigation of the Apple Vision Pro as a platform for large-scale volume visualization, focusing on both its technical capabilities and practical limitations in immersive rendering scenarios. Our study centers on BorgVR, a custom-built volume rendering system that implements a bricked, ray-guided, and out-of-core rendering pipeline tailored to the unique characteristics of the Vision Pro and the visionOS graphics stack. BorgVR is designed to overcome memory and performance bottlenecks associated with rendering structured grids that exceed device-local memory. Through dynamic data streaming, hierarchical bricking, GPU-accelerated early ray termination and empty-space skipping, the system achieves interactive frame rates for gigabyte-scale datasets, even under the constraints of mobile spatial computing. We analyze how well the Apple Vision Pro supports such workloads across its distinct rendering modes. Beyond demonstrating system performance, we evaluate the Vision Pro's suitability for scientific visualization-highlighting its strengths in display fidelity and sensor integration, while also documenting friction points such as GPU architecture constraints, memory management, and platform-specific development hurdles. The open-source release of BorgVR provides a reusable foundation for the community, facilitating future research and application development in immersive volume visualization.
Learning Neural Antiderivatives
(The Eurographics Association, 2025) Rubab, Fizza; Nsampi, Ntumba Elie; Balint, Martin; Mujkanovic, Felix; Seidel, Hans-Peter; Ritschel, Tobias; Leimkühler, Thomas; Egger, Bernhard; Günther, Tobias
Neural fields offer continuous, learnable representations that extend beyond traditional discrete formats in visual computing. We study the problem of learning neural representations of repeated antiderivatives directly from a function, a continuous analogue of summed-area tables. Although widely used in discrete domains, such cumulative schemes rely on grids, which prevents their applicability in continuous neural contexts. We introduce and analyze a range of neural methods for repeated integration, including both adaptations of prior work and novel designs. Our evaluation spans multiple input dimensionalities and integration orders, assessing both reconstruction quality and performance in downstream tasks such as filtering and rendering. These results enable integrating classical cumulative operators into modern neural systems and offer insights into learning tasks involving differential and integral operators.
Neural Acquisition & Representation of Subsurface Scattering
(The Eurographics Association, 2025) Majumdar, Arjun; Braun, Raphael; Lensch, Hendrik; Egger, Bernhard; Günther, Tobias
We present a method to acquire and estimate the sub-surface scattering properties of light transport at a highly detailed level by learning the pixel footprint response at each point on the object surface. The reconstruction leverages 3D scanning techniques as input to a U-Net CNN. A stereo projector-camera setup using phase-shifted profilometry (PSP) patterns efficiently captures the data for a variety of scattering objects. Reconstructing dense pixel footprints allows for relighting with arbitrary high-resolution projector patterns. The final output is a relit color image. Qualitative and quantitative comparison against illuminated realworld captured images demonstrate that the predicted footprints are almost identical to the actual responses. The same model is trained for multiple views across multiple objects such that the learned representations can be used to generalize to unseen sub-surface scattering materials as well.
Quantised Global Autoencoder: A Holistic Approach to Representing Visual Data
(The Eurographics Association, 2025) Elsner, Tim; Usinger, Paula; Czech, Victor; Kobsik, Gregor; He, Yanjiang; Lim, Isaak; Kobbelt, Leif; Egger, Bernhard; Günther, Tobias
Quantised autoencoders usually split images into local patches, each encoded by one token. This representation is potentially inefficient, as the same number of tokens are spent per region, regardless of the visual information content in that region. To mitigate uneven distribution of information content, modern architectures provide an adaptive discretisation or add an attention mechanism to the autoencoder to infuse global information into the local tokens. Despite these improvements, tokens are still associated with a local image region. In contrast, our method is inspired by spectral decompositions which transform an input signal into a superposition of global frequencies. Taking the data-driven perspective, we train an encoder that produces a combination of tokens that are then decoded jointly, going beyond the simple linear superposition of spectral decompositions. We achieve this global description with an efficient transpose operation between features and channels and demonstrate how our global and holistic representation improves compression and can boost downstream tasks like generation.
Quantized FCA: Efficient Zero-Shot Texture Anomaly Detection
(The Eurographics Association, 2025) Ardelean, Andrei-Timotei; Rückbeil, Patrick; Weyrich, Tim; Egger, Bernhard; Günther, Tobias
Zero-shot anomaly localization is a rising field in computer vision research, with important progress in recent years. This work focuses on the problem of detecting and localizing anomalies in textures, where anomalies can be defined as the regions that deviate from the overall statistics, violating the stationarity assumption. The main limitation of existing methods is their high running time, making them impractical for deployment in real-world scenarios, such as assembly line monitoring. We propose a real-time method, named QFCA, which implements a quantized version of the feature correspondence analysis (FCA) algorithm. By carefully adapting the patch statistics comparison to work on histograms of quantized values, we obtain a 10× speedup with little to no loss in accuracy. Moreover, we introduce a feature preprocessing step based on principal component analysis, which enhances the contrast between normal and anomalous features, improving the detection precision on complex textures. Our method is thoroughly evaluated against prior art, comparing favorably with existing methods. Project page: reality.tf.fau.de/pub/ardelean2025quantized.html.
Refinement of Monocular Depth Maps via Multi-View Differentiable Rendering
(The Eurographics Association, 2025) Fink, Laura; Franke, Linus; Egger, Bernhard; Keinert, Joachim; Stamminger, Marc; Egger, Bernhard; Günther, Tobias
Accurate depth estimation is at the core of many applications in computer graphics, vision, and robotics. Current state-ofthe- art monocular depth estimators, trained on extensive datasets, generalize well but lack 3D consistency needed for many applications. In this paper, we combine the strength of those generalizing monocular depth estimation techniques with multiview data by framing this as an analysis-by-synthesis optimization problem to lift and refine such relative depth maps to accurate error-free depth maps. After an initial global scale estimation through structure-from-motion point clouds, we further refine the depth map through optimization enforcing multi-view consistency via photometric and geometric losses with differentiable rendering of the meshed depth map. In a two-stage optimization, scaling is further refined first, and afterwards artifacts and errors in the depth map are corrected via nearby-view photometric supervision. Our evaluation shows that our method is able to generate detailed, high-quality, view consistent, accurate depth maps, also in challenging indoor scenarios, and outperforms state-of-the-art multi-view depth reconstruction approaches on such datasets. Project page and source code can be found at https://lorafib.github.io/ref_depth/.
Robust Discrete Differential Operators for Wild Geometry
(The Eurographics Association, 2025) Wagner, Sven Dominik; Botsch, Mario; Egger, Bernhard; Günther, Tobias
Many geometry processing algorithms rely on solving PDEs on discrete surface meshes. Their accuracy and robustness crucially depend on the mesh quality, which oftentimes cannot be guaranteed - in particular when automatically processing geometries extracted from arbitrary implicit representations. Through extensive numerical experiments, we evaluate the robustness of various Laplacian implementations across geometry processing libraries on synthetic and ''in-the-wild'' surface meshes with degenerate or near-degenerate elements, revealing their strengths, weaknesses, and failure cases. To improve numerical stability, we extend the recently proposed tempered finite elements method (TFEM) to meshes with strongly varying element sizes, to arbitrary polygonal elements, and to gradient and divergence operators. Our resulting differential operators are simple to implement, efficient to compute, and robust even in the presence of fully degenerate mesh elements.
Towards Integrating Multi-Spectral Imaging with Gaussian Splatting
(The Eurographics Association, 2025) Grün, Josef; Meyer, Lukas; Weiherer, Maximilian; Egger, Bernhard; Stamminger, Marc; Franke, Linus; Egger, Bernhard; Günther, Tobias
We present a study of how to integrate color (RGB) and multi-spectral imagery (red, green, red-edge, and near-infrared) into the 3D Gaussian Splatting (3DGS) framework - a state-of-the-art explicit radiance-field-based method for fast and high-fidelity 3D reconstruction from multi-view images [KKLD23]. While 3DGS excels on RGB data, naïve per-band optimization of additional spectra yields poor reconstructions due to inconsistently appearing geometry in the spectral domain. This problem is prominent, even though the actual geometry is the same, regardless of spectral modality. To investigate this, we evaluate three strategies: 1) Separate per-band reconstruction with no shared structure; 2) Splitting optimization, in which we first optimize RGB geometry, copy it, and then fit each new band to the model by optimizing both geometry and band representation; and 3) Joint, in which the modalities are jointly optimized, optionally with an initial RGB-only phase. We showcase through quantitative metrics and qualitative novel-view renderings on multi-spectral datasets the effectiveness of our dedicated optimized Joint strategy, increasing overall spectral reconstruction as well as enhancing RGB results through spectral cross-talk. We therefore suggest integrating multi-spectral data directly into the spherical harmonics color components to compactly model each Gaussian's multi-spectral reflectance. Moreover, our analysis reveals several key trade-offs in when and how to introduce spectral bands during optimization, offering practical insights for robust multi-modal 3DGS reconstruction. The project page and code is located at: meyerls.github.io/towards_multi_spec_splat
Uncovering Relations in High-Dimensional Behavioral Data of Drosophila Melanogaster
(The Eurographics Association, 2025) Thane, Michael; Blum, Kai Michael; Lehmann, Dirk J.; Egger, Bernhard; Günther, Tobias
Understanding how behaviour changes under genetic or experimental conditions is a key challenge in behavioural neuroscience. High-throughput tracking enables the collection of high-dimensional datasets describing locomotion, posture, and stimulus orientation in Drosophila melanogaster larvae (fruit fly). However, exploring relations across numerous dimensions remains challenging. We present a Visual Analytics system that integrates coordinated views, type-aware relation metrics, and hierarchical clustering to support relation discovery and validation in behavioural data. The system was initially developed based on prior experience and refined through evaluation with domain experts to address key analysis tasks, including grouping dimensions, exploring behavioural patterns, and validating hypotheses. We demonstrate how it supports both confirmatory and exploratory workflows, enabling users to confirm known effects and uncover novel patterns-such as an unexpected correlation between head-casting behaviour and locomotion speed. This work highlights how tailored visual analysis can advance behavioural research.
Val-LLM: A Visual Analytics Approach for the Critical Validation of LLM-Generated Tabular Data
(The Eurographics Association, 2025) Sachdeva, Madhav; Narayanan, Christopher; Wiedenkeller, Marvin; Sedlakova, Jana; Bernard, Jürgen; Egger, Bernhard; Günther, Tobias
Large Language Models (LLMs) are emerging as promising approaches for tabular data generation and enrichment, helping to ease constraints related to data availability. However, the reliable use of LLM-generated data remains challenging, e.g., due to hallucinations and inconsistencies. While some validation approaches exist, five key challenges remain: the lack of explanations and transparency in how values are generated, balancing fine-grained accurate with coarse-grained scalable validation, validating generated data without ground truth, and evaluating plausibility, semantic relevance, and downstream utility. To address these challenges, we present Val-LLM, a novel visual analytics approach for the critical validation of LLM-generated tabular data. Val-LLM enables users to contextualize generated data values with explanations, externalize human expert knowledge, relate LLM outputs with existing data, and assess the data utility in an application downstream. We conducted a user study to evaluate Val-LLM. Results highlight the usefulness of supporting multiple levels of granularity and enabling human knowledge externalization for validation. The study also indicates the need to study validation workflows and workflow flexibility, based on user domain experience and user preferences. Our work supports the trustworthy and effective use of LLM-generated tabular data by integrating visual analytics for systematic data validation.

Browse

Browsing VMV2025 by Title

Results Per Page

Sort Options