Marek Kowalski

EDBT 2026 Demo / reviewers in the wild / expert

dblp:84/2182 · DBLP profile ↗

← Back

16ranked-venue papers

5as first author

7since 2021 · last 2025

—ORCID · conflict

Domains — the database's venue-derived domains; a paper can count in several

Graphics, computer vision, multimedia, augmented reality and games · 12 · 4 first-author · 7 since 2021Artificial intelligence and machine learning · 9 · 1 first-author · 5 since 2021Systems, architecture and hardware · 1Theory of computation · 1 · 1 first-author

Year	Publication	Venue	Position
2025	GASP: Gaussian Avatars with Synthetic Priors abstract Gaussian Splatting has changed the game for real-time photo-realistic rendering. One of the most popular applications of Gaussian Splatting is to create animatable avatars, known as Gaussian Avatars. Recent works have pushed the boundaries of quality and rendering efficiency but suffer from two main limitations. Either they require expensive multi-camera rigs to produce avatars with free-viewpoint rendering, or they can be trained with a single camera but only rendered at high quality from this fixed viewpoint. An ideal model would be trained using a short monocular video or image from available hardware, such as a webcam, and rendered from any view. To this end, we propose GASP: Gaussian Avatars with Synthetic Priors. To overcome the limitations of existing datasets, we exploit the pixel-perfect nature of synthetic data to train a Gaussian Avatar prior. By fitting this prior model to a single photo or video and fine-tuning it, we get a high-quality Gaussian Avatar, which supports 360° rendering. Our prior is only required for fitting, not inference, enabling real-time applications. Through our method, we obtain high-quality, animatable Avatars from limited data which can be animated and rendered at 70fps on commercial hardware. Jack R. Saunders, Charlie Hewitt, Yanan Jian, Marek Kowalski, Tadas Baltrusaitis, Yiye Chen, Darren Cosker, Virginia Estellers, Nicholas Gyde, Vinay P. Namboodiri, Ben Lundell	CVPR	4
2025	VoluMe - Authentic 3D Video Calls from Live Gaussian Splat Prediction Martin de La Gorce, Charlie Hewitt, Robert Gerdisch, Zafiirah Hosenie, Givi Meishvili, Marek Kowalski, Thomas J. Cashman 0001, Antonio Criminisi	ICCV	7
2025	LumiGauss: Relightable Gaussian Splatting in the Wild abstract Decoupling lighting from geometry using unconstrained photo collections is notoriously challenging. Solving it would benefit many users as creating complex 3D assets takes days of manual labor. Many previous works have attempted to address this issue, often at the expense of output fidelity, which questions the practicality of such methods. We introduce LumiGauss - a technique that tackles 3D reconstruction of scenes and environmental lighting through 2D Gaussian Splatting. Our approach yields high-quality scene reconstructions and enables realistic lighting synthesis under novel environment maps. We also propose a method for enhancing the quality of shadows, common in outdoor scenes, by exploiting spherical harmonics properties. Our approach facilitates seamless integration with game engines and enables the use of fast precomputed radiance transfer. We validate our method on the NeRF-OSR dataset, demonstrating superior performance over baseline methods. Moreover, LumiGauss can synthesize realistic images for unseen environment maps. Our code: https://github.com/joaxkal/lumigauss. Joanna Kaleta, Kacper Kania, Tomasz Trzcinski, Marek Kowalski	WACV	4
2024	VolTeMorph: Real-time, Controllable and Generalizable Animation of Volumetric Representations abstract Abstract The recent increase in popularity of volumetric representations for scene reconstruction and novel view synthesis has put renewed focus on animating volumetric content at high visual quality and in real‐time. While implicit deformation methods based on learned functions can produce impressive results, they are ‘black boxes’ to artists and content creators, they require large amounts of training data to generalize meaningfully, and they do not produce realistic extrapolations outside of this data. In this work, we solve these issues by introducing a volume deformation method which is real‐time even for complex deformations, easy to edit with off‐the‐shelf software and can extrapolate convincingly. To demonstrate the versatility of our method, we apply it in two scenarios: physics‐based object deformation and telepresence where avatars are controlled using blendshapes. We also perform thorough experiments showing that our method compares favourably to both volumetric approaches combined with implicit deformation and methods based on mesh deformation. Stephan J. Garbin, Marek Kowalski, Virginia Estellers, Stanislaw Szymanowicz, Shideh Rezaeifar, Jingjing Shen, Matthew Johnson 0003, Julien Valentin	Comput. Graph. Forum	2
2023	BlendFields: Few-Shot Example-Driven Facial Modeling abstract Generating faithful visualizations of human faces requires capturing both coarse and fine-level details of the face geometry and appearance. Existing methods are either data-driven, requiring an extensive corpus of data not publicly accessible to the research community, or fail to capture fine details because they rely on geometric face models that cannot represent fine-grained details in texture with a mesh discretization and linear deformation designed to model only a coarse face geometry. We introduce a method that bridges this gap by drawing inspiration from traditional computer graphics techniques. Unseen expressions are modeled by blending appearance from a sparse set of extreme poses. This blending is performed by measuring local volumetric changes in those expressions and locally reproducing their appearance whenever a similar expression is performed at test time. We show that our method generalizes to unseen expressions, adding fine-grained effects on top of smooth volumetric deformations of a face, and demonstrate how it generalizes beyond faces. Kacper Kania, Stephan J. Garbin, Andrea Tagliasacchi, Virginia Estellers, Kwang Moo Yi, Julien Valentin, Tomasz Trzcinski, Marek Kowalski	CVPR	8
2022	CoNeRF: Controllable Neural Radiance Fields abstract We extend neural 3D representations to allow for intu-itive and interpretable user control beyond novel view ren-dering (i. e. camera control). We allow the user to annotate which part of the scene one wishes to control with just a small number of mask annotations in the training images. Our key idea is to treat the attributes as latent variables that are regressed by the neural network given the scene en-coding. This leads to afew-shot learning framework, where attributes are discovered automatically by the framework, when annotations are not provided. We apply our method to various scenes with different types of controllable attributes (e.g. expression control on human faces, or state control in movement of inanimate objects). Overall, we demonstrate, to the best of our knowledge, for the first time novel view and novel attribute re-rendering of scenes from a single video. Kacper Kania, Kwang Moo Yi, Marek Kowalski, Tomasz Trzcinski, Andrea Tagliasacchi	CVPR	3
2021	FastNeRF: High-Fidelity Neural Rendering at 200FPS abstract Recent work on Neural Radiance Fields (NeRF) showed how neural networks can be used to encode complex 3D environments that can be rendered photorealistically from novel viewpoints. Rendering these images is very computationally demanding and recent improvements are still a long way from enabling interactive rates, even on high-end hardware. Motivated by scenarios on mobile and mixed reality devices, we propose FastNeRF, the first NeRF-based system capable of rendering high fidelity photorealistic images at 200Hz on a high-end consumer GPU. The core of our method is a graphics-inspired factorization that allows for (i) compactly caching a deep radiance map at each position in space, (ii) efficiently querying that map using ray directions to estimate the pixel values in the rendered image. Extensive experiments show that the proposed method is 3000 times faster than the original NeRF algorithm and at least an order of magnitude faster than existing work on accelerating NeRF, while maintaining visual quality and extensibility. Stephan J. Garbin, Marek Kowalski, Matthew Johnson 0003, Jamie Shotton, Julien P. C. Valentin	ICCV	2
2020	High Resolution Zero-Shot Domain Adaptation of Synthetically Rendered Face Images Stephan J. Garbin, Marek Kowalski, Matthew Johnson 0003, Jamie Shotton	ECCV (28)	2
2020	CONFIG: Controllable Neural Face Image Generation Marek Kowalski, Stephan J. Garbin, Virginia Estellers, Tadas Baltrusaitis, Matthew Johnson 0003, Jamie Shotton	ECCV (11)	1
2018	HoloFace: Augmenting Human-to-Human Interactions on HoloLens abstract We present HoloFace, an open-source framework for face alignment, head pose estimation and facial attribute retrieval for Microsoft HoloLens. HoloFace implements two state-of-the-art face alignment methods which can be used interchangeably: one running locally and one running on a remote backend. Head pose estimation is accomplished by fitting a deformable 3D model to the landmarks localized using face alignment. The head pose provides both the rotation of the head and a position in the world space. The parameters of the fitted 3D face model provide estimates of facial attributes such as mouth opening or smile. Together the above information can be used to augment the faces of people seen by the HoloLens user, and thus their interaction. Potential usage scenarios include facial recognition, emotion recognition, eye gaze tracking and many others. We demonstrate the capabilities of our framework by augmenting the faces of people seen through the HoloLens with various objects and animations. Marek Kowalski, Zbigniew Nasarzewski, Grzegorz Galinski, Piotr Garbat	WACV	1
2017	Using a Probabilistic Neural Network for lip-based biometric verification Krzysztof Wrobel 0001, Rafal Doroz, Piotr Porwik, Jacek Naruniec, Marek Kowalski	Eng. Appl. Artif. Intell.	5
2017	Webcam-based system for video-oculography abstract Video‐oculography (VOG) is a tool providing diagnostic information about the progress of the diseases that cause regression of the vergence eye movements, such as Parkinson's disease (PD). The majority of the existing systems are based on sophisticated infra‐red (IR) devices. In this study, the authors show that a webcam‐based VOG system can provide similar accuracy to that of a head‐mounted IR‐based VOG system. They also prove that the authors’ iris localisation algorithm outperforms current state‐of‐the‐art methods on the popular BioID dataset in terms of accuracy. The proposed system consists of a set of image processing algorithms: face detection, facial features localisation and iris localisation. They have performed examinations on patients suffering from PD using their system and a JAZZ‐novo head‐mounted device with IR sensor as reference. In the experiments, they have obtained a mean correlation of 0.841 between the results from their method and those from the JAZZ‐novo. They have shown that the accuracy of their visual system is similar to the accuracy of IR head‐mounted devices. In the future, they plan to extend their experiments to inexpensive high frame rate cameras which can potentially provide more diagnostic parameters. Jacek Naruniec, Stanislaw Szlufik, Dariusz M. Koziorowski, Michal Tomaszewski, Marek Kowalski, Andrzej W. Przybyszewski	IET Comput. Vis.	6
2016	Face Alignment Using K-Cluster Regression Forests With Weighted Splitting abstract In this letter, we present a face alignment pipeline based on two novel methods: weighted splitting for K-cluster Regression Forests (KRF) and three-dimensional Affine Pose Regression (3D-APR) for face shape initialization. Our face alignment method is based on the Local Binary Feature (LBF) framework, where instead of standard regression forests and pixel difference features used in the original method, we use our K-Cluster Regression Forests with Weighted Splitting (KRFWS) and Pyramid Histogram of Oriented Gradients (PHOG) features. We also use KRFWS to perform APR and 3D-APR, which intend to improve the face shape initialization. APR applies a rigid 2-D transform to the initial face shape that compensates for inaccuracy in the initial face location, size, and in-plane rotation. 3D-APR estimates the parameters of a 3-D transform that additionally compensates for out-of-plane rotation. The resulting pipeline, consisting of APR and 3D-APR followed by face alignment, shows an improvement of 20% over standard LBF on the challenging Intelligent Behaviour Understanding Group (IBUG) dataset, and state-of-the-art accuracy on the entire 300-W dataset. Marek Kowalski, Jacek Naruniec	IEEE Signal Process. Lett.	1
2015	Live Scan3D: A Fast and Inexpensive 3D Data Acquisition System for Multiple Kinect v2 Sensors abstract LiveScan3D is a free, open source system for live, 3D data acquisition using multiple Kinect v2 sensors. It allows the user to place any number of sensors in any physical configuration and start gathering data at real time speed. The freedom of placing the sensors in any configuration allows for many possible acquisition scenarios such as: capturing a single object from many viewpoints or creating 3D panoramas with multiple devices located close to each other. Thanks to the off-the-shelf Kinect v2 sensor the system is both accurate and inexpensive, opening 3D acquisition up to more recipients. In the paper we describe our system with the algorithms it is using and show its effectiveness in multiple scenarios including head shape reconstruction and 3D reconstruction of dynamic scenes. Marek Kowalski, Jacek Naruniec, Michal Daniluk	3DV	1
2015	The IceProd framework: Distributed data processing for the IceCube neutrino observatory Mark G. Aartsen, Rasha U. Abbasi, Markus Ackermann 0003, Jenni Adams, Juan Antonio Aguilar Sánchez, Markus Ahlers, David Altmann, Carlos A. Argüelles Delgado, Jan Auffenberg, Xinhua Bai, Michael F. Baker, Steven W. Barwick, Volker Baum, Ryan Bay, James J. Beatty, Julia K. Becker Tjus, Karl-Heinz Becker, Segev BenZvi, Patrick Berghaus, David Berley, Elisa Bernardini, Anna Bernhard, David Z. Besson, G. Binder, Daniel Bindig, Martin Bissok, Erik Blaufuss, Jan Blumenthal, David J. Boersma, Christian Bohm, Debanjan Bose, Sebastian Böser, Olga Botner, Lionel Brayeur, Hans-Peter Bretz, Anthony M. Brown, Ronald Bruijn, James Casey, Martin Casier, Dmitry Chirkin, Asen Christov, Brian John Christy, Ken Clark, Lew Classen, Fabian Clevermann, Stefan Coenders, Shirit Cohen, Doug F. Cowen, Angel H. Cruz Silva, Matthias Danninger, Jacob Daughhetee, James C. Davis 0002, Melanie Day, Catherine De Clercq, Sam De Ridder, Paolo Desiati, Krijn D. de Vries, Meike de With, Tyce DeYoung, Juan Carlos Díaz-Vélez, Matthew Dunkman, Ryan Eagan, Benjamin Eberhardt, Björn Eichmann, Jonathan Eisch, Sebastian Euler, Paul A. Evenson, Oladipo O. Fadiran, Ali R. Fazely, Anatoli Fedynitch, Jacob Feintzeig, Tom Feusels, Kirill Filimonov, Chad Finley, Tobias Fischer-Wasels, Samuel Flis, Anna Franckowiak, Katharina Frantzen, Tomasz Fuchs, Thomas K. Gaisser, Joseph S. Gallagher, Lisa Gerhardt, Laura E. Gladstone, Thorsten Glüsenkamp, Azriel Goldschmidt, Geraldina Golup, Javier G. González, Jordan A. Goodman, Dariusz Góra, Dylan T. Grandmont, Darren Grant, Pavel Gretskov, John C. Groh, Andreas Groß, Chang Hyon Ha, Abd Al Karim Haj Ismail, Patrick Hallen, Allan Hallgren, Francis Halzen, Kael D. Hanson, Dustin Hebecker, David Heereman, Dirk Heinen, Klaus Helbing, Robert Eugene Hellauer III, Stephanie Virginia Hickford, Gary C. Hill, Kara D. Hoffman, Ruth Hoffmann, Andreas Homeier, Kotoyo Hoshina, Feifei Huang, Warren Huelsnitz, Per Olof Hulth, Klas Hultqvist, Aya Ishihara, Emanuel Jacobi, John E. Jacobsen, Kai Jagielski, George S. Japaridze, Kyle Jero, Ola Jlelati, Basho Kaminsky, Alexander Kappes, Timo Karg, Albrecht Karle, Matthew Kauer, John Lawrence Kelley, Joanna Kiryluk, J. Kläs, Spencer R. Klein, Jan-Hendrik Köhne, Georges Kohnen, Hermann Kolanoski, Lutz Köpke, Claudio Kopper, Sandro Kopper, D. Jason Koskinen, Marek Kowalski, Mark Krasberg, Anna Kriesten, Kai Michael Krings, Gösta Kroll, Jan Kunnen, Naoko Kurahashi, Takao Kuwabara, Mathieu L. M. Labare, Hagar Landsman, Michael James Larson, Mariola Lesiak-Bzdak, Martin Leuermann, Julia Leute, Jan Lünemann, Oscar A. Macías-Ramírez, James Madsen, Giuliano Maggi, Reina Maruyama, Keiichi Mase, Howard S. Matis, Frank McNally, Kevin James Meagher, Martin Merck, Gonzalo Merino, Thomas Meures, Sandra Miarecki, Eike Middell, Natalie Milke, John Lester Miller, Lars Mohrmann, Teresa Montaruli, Robert M. Morse, Rolf Nahnhauer, Uwe Naumann, Hans Niederhausen, Sarah C. Nowicki, David R. Nygren, Anna Pollmann, Sirin Odrowski, Alex Olivas, Ahmad Omairat, Aongus Starbuck Ó Murchadha, Larissa Paul, Joshua A. Pepper, Carlos Pérez de los Heros, Carl Pfendner, Damian Pieloth, Elisa Pinat, Jonas Posselt, P. Buford Price, Gerald T. Przybylski, Melissa Quinnan, Leif Rädel, Ian Rae, Mohamed Rameez, Katherine Rawlins, Peter Christian Redl, René Reimann, Elisa Resconi, Wolfgang Rhode, Mathieu Ribordy, Michael Richman, Benedikt Riedel, J. P. Rodrigues, Carsten Rott, Tim Ruhe, Bakhtiyar Ruzybayev, Dirk Ryckbosch, Sabine M. Saba, Heinz-Georg Sander, Juan Marcos Santander, Subir Sarkar 0002, Kai Schatto, Florian Scheriau, Torsten Schmidt, Martin Schmitz 0004, Sebastian Schoenen, Sebastian Schöneberg, Arne Schönwald, Anne Schukraft, Lukas Schulte, David Schultz, Olaf Schulz, David Seckel, Yolanda Sestayo de la Cerra, Surujhdeo Seunarine, Rezo Shanidze, Chris Sheremata, Miles W. E. Smith, Dennis Soldin, Glenn M. Spiczak, Christian Spiering, Michael Stamatikos, Todor Stanev, Nick A. Stanisha, Alexander Stasik, Thorsten Stezelberger, Robert G. Stokstad, Achim Stößl, Erik A. Strahler, Rickard Ström, Nora Linn Strotjohann, Gregory W. Sullivan, Henric Taavola, Ignacio J. Taboada, Alessio Tamburro, Andreas Tepe, Samvel Ter-Antonyan, Gordana Tesic, Serap Tilav, Patrick A. Toale, Moriah Natasha Tobin, Simona Toscano, Maria Tselengidou, Elisabeth Unger, Marcel Usner, Sofia Vallecorsa, Nick van Eijndhoven, Arne Van Overloop, Jakob van Santen, Markus Vehring, Markus Voge, Matthias Vraeghe, Christian Walck, Tilo Waldenmaier, Marius Wallraff, Christopher Weaver 0001, Mark T. Wellons, Christopher H. Wendt, Stefan Westerhoff, Nathan Whitehorn, Klaus Wiebe, Christopher H. Wiebusch, Dawn R. Williams, Henrike Wissing, Martin Wolf 0007, Terri R. Wood, Kurt Woschnagg, Donglian Xu, Xianwu Xu, Juan Pablo Yáñez, Gaurang B. Yodh, Shigeru Yoshida, Pavel Zarzhitsky, Jan Ziemann, Simon Zierke, Marcel Zoll	J. Parallel Distributed Comput.	140
1988	Approximation of smooth periodic functions in several variables Marek Kowalski, Waldemar Sielski	J. Complex.	1