Felix Mujkanovic

Felix Mujkanovic

Auto-generated profile, based on publicly available information

Felix Mujkanovic

Max Planck Institute for Informatics, Saarbrücken, Germany

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 July 2024 in ACM Transactions on Graphics
Verified
Journal Article
Open access
FMFelix Mujkanovic
Felix Mujkanovic
NNNtumba Elie Nsampi
Ntumba Elie Nsampi
CTChristian Theobalt
Christian Theobalt
HSHans-Peter Seidel
Hans-Peter Seidel
TLThomas Leimkühler
Thomas Leimkühler
Gaussian scale spaces are a cornerstone of signal representation and processing, with applications in filtering, multiscale analysis, anti-aliasing, and many more. However, obtaining such a scale space is costly and cumbersome, in particular for continuous representations such as neural fields. We present an efficient and lightweight method to learn the fully continuous, anisotropic Gaussian scale space of an arbitrary signal. Based on Fourier feature modulation and Lipschitz bounding, our approach is trained self-supervised, i.e., training does not require any manual filtering. Our neural Gaussian scale-space fields faithfully capture multiscale representations across a broad range of modalities, and support a diverse set of applications. These include images, geometry, light-stage data, texture anti-aliasing, and multiscale optimization.

4 December 2025 in ACM Transactions on Graphics
Verified
Journal Article
Open access
CSChristian Stippel
Christian Stippel
FMFelix Mujkanovic
Felix Mujkanovic
TLThomas Leimkühler
Thomas Leimkühler
PHPedro Hermosilla
Pedro Hermosilla
Accurate surface geometry representation is crucial in 3D visual computing. Explicit representations, such as polygonal meshes, and implicit representations, like signed distance functions, each have distinct advantages, making efficient conversions between them increasingly important. Conventional surface extraction methods for implicit representations, such as the widely used Marching Cubes algorithm, rely on spatial decomposition and sampling, leading to inaccuracies due to fixed and limited resolution. We introduce a novel approach for analytically extracting surfaces from neural implicit functions. Our method operates natively in parallel and can navigate large neural architectures. By leveraging the fact that each neuron partitions the domain, we develop a depth-first traversal strategy to efficiently track the encoded surface. The resulting meshes faithfully capture the full geometric information from the network without ad-hoc spatial discretization, achieving unprecedented accuracy across diverse shapes and network architectures while maintaining competitive speed.

18 April 2025 in Computer Graphics Forum
Verified
Journal Article
Open access
ADA. Djeacoumar
A. Djeacoumar
FMF. Mujkanovic
F. Mujkanovic
HSH.‐P. Seidel
H.‐P. Seidel
TLT. Leimkühler
T. Leimkühler
Fractal geometry, defined by self‐similar patterns across scales, is crucial for understanding natural structures. This work addresses the fractal inverse problem, which involves extracting fractal codes from images to explain these patterns and synthesize them at arbitrary finer scales. We introduce a novel algorithm that optimizes Iterated Function System parameters using a custom fractal generator combined with differentiable point splatting. By integrating both stochastic and gradient‐based optimization techniques, our approach effectively navigates the complex energy landscapes typical of fractal inversion, ensuring robust performance and the ability to escape local minima. We demonstrate the method's effectiveness through comparisons with various fractal inversion techniques, highlighting its ability to recover high‐quality fractal codes and perform extensive zoom‐ins to reveal intricate patterns from just a single image.

24 February 2025 in arXiv
Verified
Preprint
Open access
PDF file
ADAdarsh Djeacoumar
Adarsh Djeacoumar
FMFelix Mujkanovic
Felix Mujkanovic
HSHans-Peter Seidel
Hans-Peter Seidel
TLThomas Leimkühler
Thomas Leimkühler
Fractal geometry, defined by self-similar patterns across scales, is crucial for understanding natural structures. This work addresses the fractal inverse problem, which involves extracting fractal codes from images to explain these patterns and synthesize them at arbitrary finer scales. We introduce a novel algorithm that optimizes Iterated Function System parameters using a custom fractal generator combined with differentiable point splatting. By integrating both stochastic and gradient-based optimization techniques, our approach effectively navigates the complex energy landscapes typical of fractal inversion, ensuring robust performance and the ability to escape local minima. We demonstrate the method's effectiveness through comparisons with various fractal inversion techniques, highlighting its ability to recover high-quality fractal codes and perform extensive zoom-ins to reveal intricate patterns from just a single image.

22 September 2025 in arXiv
Verified
Preprint
Open access
PDF file
FRFizza Rubab
Fizza Rubab
NNNtumba Elie Nsampi
Ntumba Elie Nsampi
MBMartin Balint
Martin Balint
FMFelix Mujkanovic
Felix Mujkanovic
HSHans-Peter Seidel
Hans-Peter Seidel
TLThomas Leimkühler
Thomas Leimkühler
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.