arXiv subjects

Elmar Eisemann

Publications and source records attributed to Elmar Eisemann.

At least 19 recordsLinked to original sources

arXiv2026

Skill-Adaptive Ghost Instructors: Enhancing Retention and Reducing Over-Reliance in VR Piano Learning

Motor-skill learning systems in XR rely on persistent cues. However, constant cueing can induce overreliance and erode memorization and skill transfer. We introduce a skill-adaptive, dynamically transparent ghost instructor whose opacity adapts in real time to learner performance. In a first-person perspective, users observe a ghost hand executing piano fingering with either a static or a performance-adaptive transparency in a VR piano training application. We conducted a within-subjects study (N=30), where learners practiced with traditional Static (fixed-transparency) and our proposed Dynamic (performance-adaptive) modes and were tested without guidance immediately and after a 10-minute retention interval. Relative to Static, the Dynamic mode yielded higher pitch and fingering accuracy and limited error increases, with comparable timing. These findings suggest that adaptive transparency helps learners internalize fingerings more effectively, reducing dependency on external cues and improving short-term skill retention within immersive learning environments. We discuss design implications for motor-skill learning and outline directions for extending this approach to longer-term retention and more complex tasks.

cs.HC↗

arXiv2026

Manifold-Preserving Superpixel Hierarchies and Embeddings for the Exploration of High-Dimensional Images

High-dimensional images, or images with a high-dimensional attribute vector per pixel, are commonly explored with coordinated views of a low-dimensional embedding of the attribute space and a conventional image representation. Nowadays, such images can easily contain several million pixels. For such large datasets, hierarchical embedding techniques are better suited to represent the high-dimensional attribute space than flat dimensionality reduction methods. However, available hierarchical dimensionality reduction methods construct the hierarchy purely based on the attribute information and ignore the spatial layout of pixels in the images. This impedes the exploration of regions of interest in the image space, since there is no congruence between a region of interest in image space and the associated attribute abstractions in the hierarchy. In this paper, we present a superpixel hierarchy for high-dimensional images that takes the high-dimensional attribute manifold into account during construction. Through this, our method enables consistent exploration of high-dimensional images in both image and attribute space. We show the effectiveness of this new image-guided hierarchy in the context of embedding exploration by comparing it with classical hierarchical embedding-based image exploration in two use cases.

cs.CV↗

arXiv2025

Surface-Aware Distilled 3D Semantic Features

Many 3D tasks such as pose alignment, animation, motion transfer, and 3D reconstruction rely on establishing correspondences between 3D shapes. This challenge has recently been approached by pairwise matching of semantic features from pre-trained vision models. However, despite their power, these features struggle to differentiate instances of the same semantic class such as ``left hand'' versus ``right hand'' which leads to substantial mapping errors. To solve this, we learn a surface-aware embedding space that is robust to these ambiguities while facilitating shared mapping for an entire family of 3D shapes. Importantly, our approach is self-supervised and requires only a small number of unpaired training meshes to infer features for new possibly imperfect 3D shapes at test time. We achieve this by introducing a contrastive loss that preserves the semantic content of the features distilled from foundational models while disambiguating features located far apart on the shape's surface. We observe superior performance in correspondence matching benchmarks and enable downstream applications including 2D-to-3D and 3D-to-3D texture transfer, in-part segmentation, pose alignment, and motion transfer in low-data regimes. Unlike previous pairwise approaches, our solution constructs a joint embedding space, where both seen and unseen 3D shapes are implicitly aligned without further optimization. The code is available at https://graphics.tudelft.nl/SurfaceAware3DFeatures.

cs.CV↗

arXiv2025

Uncertainty for SVBRDF Acquisition using Frequency Analysis

This paper aims to quantify uncertainty for SVBRDF acquisition in multi-view captures. Under uncontrolled illumination and unstructured viewpoints, there is no guarantee that the observations contain enough information to reconstruct the appearance properties of a captured object. We study this ambiguity, or uncertainty, using entropy and accelerate the analysis by using the frequency domain, rather than the domain of incoming and outgoing viewing angles. The result is a method that computes a map of uncertainty over an entire object within a millisecond. We find that the frequency model allows us to recover SVBRDF parameters with competitive performance, that the accelerated entropy computation matches results with a physically-based path tracer, and that there is a positive correlation between error and uncertainty. We then show that the uncertainty map can be applied to improve SVBRDF acquisition using capture guidance, sharing information on the surface, and using a diffusion model to inpaint uncertain regions. Our code is available at https://github.com/rubenwiersma/svbrdf_uncertainty.

cs.CV↗

arXiv2024

Navigating Perplexity: A linear relationship with the data set size in t-SNE embeddings

Widely used pipelines for analyzing high-dimensional data utilize two-dimensional visualizations. These are created, for instance, via t-distributed stochastic neighbor embedding (t-SNE). A crucial element of the t-SNE embedding procedure is the perplexity hyperparameter. That is because the embedding structure varies when perplexity is changed. A suitable perplexity choice depends on the data set and the intended usage for the embedding. Therefore, perplexity is often chosen based on heuristics, intuition, and prior experience. This paper uncovers a linear relationship between perplexity and the data set size. Namely, we show that embeddings remain structurally consistent across data set samples when perplexity is adjusted accordingly. Qualitative and quantitative experimental results support these findings. This informs the visualization process, guiding the user when choosing a perplexity value. Finally, we outline several applications for the visualization of high-dimensional data via t-SNE based on this linear relationship.

cs.LG↗

arXiv2024

MotionDreamer: Exploring Semantic Video Diffusion features for Zero-Shot 3D Mesh Animation

Animation techniques bring digital 3D worlds and characters to life. However, manual animation is tedious and automated techniques are often specialized to narrow shape classes. In our work, we propose a technique for automatic re-animation of various 3D shapes based on a motion prior extracted from a video diffusion model. Unlike existing 4D generation methods, we focus solely on the motion, and we leverage an explicit mesh-based representation compatible with existing computer-graphics pipelines. Furthermore, our utilization of diffusion features enhances accuracy of our motion fitting. We analyze efficacy of these features for animation fitting and we experimentally validate our approach for two different diffusion models and four animation models. Finally, we demonstrate that our time-efficient zero-shot method achieves a superior performance re-animating a diverse set of 3D shapes when compared to existing techniques in a user study. The project website is located at https://lukas.uzolas.com/MotionDreamer.

cs.CV↗

arXiv2024

RANRAC: Robust Neural Scene Representations via Random Ray Consensus

Learning-based scene representations such as neural radiance fields or light field networks, that rely on fitting a scene model to image observations, commonly encounter challenges in the presence of inconsistencies within the images caused by occlusions, inaccurately estimated camera parameters or effects like lens flare. To address this challenge, we introduce RANdom RAy Consensus (RANRAC), an efficient approach to eliminate the effect of inconsistent data, thereby taking inspiration from classical RANSAC based outlier detection for model fitting. In contrast to the down-weighting of the effect of outliers based on robust loss formulations, our approach reliably detects and excludes inconsistent perspectives, resulting in clean images without floating artifacts. For this purpose, we formulate a fuzzy adaption of the RANSAC paradigm, enabling its application to large scale models. We interpret the minimal number of samples to determine the model parameters as a tunable hyperparameter, investigate the generation of hypotheses with data-driven models, and analyze the validation of hypotheses in noisy environments. We demonstrate the compatibility and potential of our solution for both photo-realistic robust multi-view reconstruction from real-world images based on neural radiance fields and for single-shot reconstruction based on light-field networks. In particular, the results indicate significant improvements compared to state-of-the-art robust methods for novel-view synthesis on both synthetic and captured scenes with various inconsistencies including occlusions, noisy camera pose estimates, and unfocused perspectives. The results further indicate significant improvements for single-shot reconstruction from occluded images. Project Page: https://bennobuschmann.com/ranrac/

cs.CV↗

arXiv2024

Accelerating hyperbolic t-SNE

The need to understand the structure of hierarchical or high-dimensional data is present in a variety of fields. Hyperbolic spaces have proven to be an important tool for embedding computations and analysis tasks as their non-linear nature lends itself well to tree or graph data. Subsequently, they have also been used in the visualization of high-dimensional data, where they exhibit increased embedding performance. However, none of the existing dimensionality reduction methods for embedding into hyperbolic spaces scale well with the size of the input data. That is because the embeddings are computed via iterative optimization schemes and the computation cost of every iteration is quadratic in the size of the input. Furthermore, due to the non-linear nature of hyperbolic spaces, Euclidean acceleration structures cannot directly be translated to the hyperbolic setting. This paper introduces the first acceleration structure for hyperbolic embeddings, building upon a polar quadtree. We compare our approach with existing methods and demonstrate that it computes embeddings of similar quality in significantly less time. Implementation and scripts for the experiments can be found at https://graphics.tudelft.nl/accelerating-hyperbolic-tsne.

cs.HC↗

arXiv2023

ManiVault: A Flexible and Extensible Visual Analytics Framework for High-Dimensional Data

Exploration and analysis of high-dimensional data are important tasks in many fields that produce large and complex data, like the financial sector, systems biology, or cultural heritage. Tailor-made visual analytics software is developed for each specific application, limiting their applicability in other fields. However, as diverse as these fields are, their characteristics and requirements for data analysis are conceptually similar. Many applications share abstract tasks and data types and are often constructed with similar building blocks. Developing such applications, even when based mostly on existing building blocks, requires significant engineering efforts. We developed ManiVault, a flexible and extensible open-source visual analytics framework for analyzing high-dimensional data. The primary objective of ManiVault is to facilitate rapid prototyping of visual analytics workflows for visualization software developers and practitioners alike. ManiVault is built using a plugin-based architecture that offers easy extensibility. While our architecture deliberately keeps plugins self-contained, to guarantee maximum flexibility and re-usability, we have designed and implemented a messaging API for tight integration and linking of modules to support common visual analytics design patterns. We provide several visualization and analytics plugins, and ManiVault's API makes the integration of new plugins easy for developers. ManiVault facilitates the distribution of visualization and analysis pipelines and results for practitioners through saving and reproducing complete application states. As such, ManiVault can be used as a communication tool among researchers to discuss workflows and results. A copy of this paper and all supplemental material is available at https://osf.io/9k6jw and source code at https://github.com/ManiVaultStudio.

cs.HC↗

arXiv2023

Template-free Articulated Neural Point Clouds for Reposable View Synthesis

Dynamic Neural Radiance Fields (NeRFs) achieve remarkable visual quality when synthesizing novel views of time-evolving 3D scenes. However, the common reliance on backward deformation fields makes reanimation of the captured object poses challenging. Moreover, the state of the art dynamic models are often limited by low visual fidelity, long reconstruction time or specificity to narrow application domains. In this paper, we present a novel method utilizing a point-based representation and Linear Blend Skinning (LBS) to jointly learn a Dynamic NeRF and an associated skeletal model from even sparse multi-view video. Our forward-warping approach achieves state-of-the-art visual fidelity when synthesizing novel views and poses while significantly reducing the necessary learning time when compared to existing work. We demonstrate the versatility of our representation on a variety of articulated objects from common datasets and obtain reposable 3D reconstructions without the need of object-specific skeletal templates. Code will be made available at https://github.com/lukasuz/Articulated-Point-NeRF.

cs.CV↗

arXiv2023

A Fast Geometric Multigrid Method for Curved Surfaces

We introduce a geometric multigrid method for solving linear systems arising from variational problems on surfaces in geometry processing, Gravo MG. Our scheme uses point clouds as a reduced representation of the levels of the multigrid hierarchy to achieve a fast hierarchy construction and to extend the applicability of the method from triangle meshes to other surface representations like point clouds, nonmanifold meshes, and polygonal meshes. To build the prolongation operators, we associate each point of the hierarchy to a triangle constructed from points in the next coarser level. We obtain well-shaped candidate triangles by computing graph Voronoi diagrams centered around the coarse points and determining neighboring Voronoi cells. Our selection of triangles ensures that the connections of each point to points at adjacent coarser and finer levels are balanced in the tangential directions. As a result, we obtain sparse prolongation matrices with three entries per row and fast convergence of the solver.

cs.CG↗

arXiv2022

Quantifying spatial, temporal, angular and spectral structure of effective daylight in perceptually meaningful ways

We present a method to capture the 7-dimensional light field structure, and translate it into perceptually-relevant information. Our spectral cubic illumination method quantifies objective correlates of perceptually relevant diffuse and directed light components, including their variations over time, space, in color and direction, and the environment's response to sky and sunlight. We applied it 'in the wild', capturing how light on a sunny day differs between light and shadow, and how light varies over sunny and cloudy days. We discuss the added value of our method for capturing nuanced lighting effects on scene and object appearance, such as chromatic gradients.

cs.GR↗

arXiv2022

DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds

Learning from 3D point-cloud data has rapidly gained momentum, motivated by the success of deep learning on images and the increased availability of 3D~data. In this paper, we aim to construct anisotropic convolution layers that work directly on the surface derived from a point cloud. This is challenging because of the lack of a global coordinate system for tangential directions on surfaces. We introduce DeltaConv, a convolution layer that combines geometric operators from vector calculus to enable the construction of anisotropic filters on point clouds. Because these operators are defined on scalar- and vector-fields, we separate the network into a scalar- and a vector-stream, which are connected by the operators. The vector stream enables the network to explicitly represent, evaluate, and process directional information. Our convolutions are robust and simple to implement and match or improve on state-of-the-art approaches on several benchmarks, while also speeding up training and inference.

cs.CV↗

arXiv2022

Deep vanishing point detection: Geometric priors make dataset variations vanish

Deep learning has improved vanishing point detection in images. Yet, deep networks require expensive annotated datasets trained on costly hardware and do not generalize to even slightly different domains, and minor problem variants. Here, we address these issues by injecting deep vanishing point detection networks with prior knowledge. This prior knowledge no longer needs to be learned from data, saving valuable annotation efforts and compute, unlocking realistic few-sample scenarios, and reducing the impact of domain changes. Moreover, the interpretability of the priors allows to adapt deep networks to minor problem variations such as switching between Manhattan and non-Manhattan worlds. We seamlessly incorporate two geometric priors: (i) Hough Transform -- mapping image pixels to straight lines, and (ii) Gaussian sphere -- mapping lines to great circles whose intersections denote vanishing points. Experimentally, we ablate our choices and show comparable accuracy to existing models in the large-data setting. We validate our model's improved data efficiency, robustness to domain changes, adaptability to non-Manhattan settings.

cs.CV↗

arXiv2022

Incorporating Texture Information into Dimensionality Reduction for High-Dimensional Images

High-dimensional imaging is becoming increasingly relevant in many fields from astronomy and cultural heritage to systems biology. Visual exploration of such high-dimensional data is commonly facilitated by dimensionality reduction. However, common dimensionality reduction methods do not include spatial information present in images, such as local texture features, into the construction of low-dimensional embeddings. Consequently, exploration of such data is typically split into a step focusing on the attribute space followed by a step focusing on spatial information, or vice versa. In this paper, we present a method for incorporating spatial neighborhood information into distance-based dimensionality reduction methods, such as t-Distributed Stochastic Neighbor Embedding (t-SNE). We achieve this by modifying the distance measure between high-dimensional attribute vectors associated with each pixel such that it takes the pixel's spatial neighborhood into account. Based on a classification of different methods for comparing image patches, we explore a number of different approaches. We compare these approaches from a theoretical and experimental point of view. Finally, we illustrate the value of the proposed methods by qualitative and quantitative evaluation on synthetic data and two real-world use cases.

cs.CV↗

arXiv2020

CNNs on Surfaces using Rotation-Equivariant Features

This paper is concerned with a fundamental problem in geometric deep learning that arises in the construction of convolutional neural networks on surfaces. Due to curvature, the transport of filter kernels on surfaces results in a rotational ambiguity, which prevents a uniform alignment of these kernels on the surface. We propose a network architecture for surfaces that consists of vector-valued, rotation-equivariant features. The equivariance property makes it possible to locally align features, which were computed in arbitrary coordinate systems, when aggregating features in a convolution layer. The resulting network is agnostic to the choices of coordinate systems for the tangent spaces on the surface. We implement our approach for triangle meshes. Based on circular harmonic functions, we introduce convolution filters for meshes that are rotation-equivariant at the discrete level. We evaluate the resulting networks on shape correspondence and shape classifications tasks and compare their performance to other approaches.

cs.CV↗

arXiv2019

LightGuider: Guiding Interactive Lighting Design using Suggestions, Provenance, and Quality Visualization

LightGuider is a novel guidance-based approach to interactive lighting design, which typically consists of interleaved 3D modeling operations and light transport simulations. Rather than having designers use a trial-and-error approach to match their illumination constraints and aesthetic goals, LightGuider supports the process by simulating potential next modeling steps that can deliver the most significant improvements. LightGuider takes predefined quality criteria and the current focus of the designer into account to visualize suggestions for lighting-design improvements via a specialized provenance tree. This provenance tree integrates snapshot visualizations of how well a design meets the given quality criteria weighted by the designer's preferences. This integration facilitates the analysis of quality improvements over the course of a modeling workflow as well as the comparison of alternative design solutions. We evaluate our approach with three lighting designers to illustrate its usefulness.

cs.GR↗

arXiv2019

How to Manipulate CNNs to Make Them Lie: the GradCAM Case

Recently many methods have been introduced to explain CNN decisions. However, it has been shown that some methods can be sensitive to manipulation of the input. We continue this line of work and investigate the explanation method GradCAM. Instead of manipulating the input, we consider an adversary that manipulates the model itself to attack the explanation. By changing weights and architecture, we demonstrate that it is possible to generate any desired explanation, while leaving the model's accuracy essentially unchanged. This illustrates that GradCAM cannot explain the decision of every CNN and provides a proof of concept showing that it is possible to obfuscate the inner workings of a CNN. Finally, we combine input and model manipulation. To this end we put a backdoor in the network: the explanation is correct unless there is a specific pattern present in the input, which triggers a malicious explanation. Our work raises new security concerns, especially in settings where explanations of models may be used to make decisions, such as in the medical domain.

cs.CV↗