Weronika Smolak-Dyżewska
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Weronika Smolak-Dyżewska has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Przemysław Spurek
Jagiellonian University
5 shared publications Dawid Malarz
4 shared publications- Marcin Mazur
Faculty of Mathematics and Computer Science, Jagiellonian University
3 shared publications - Grzegorz Wilczyński
Jagiellonian University
2 shared publications Jan Kaczmarczyk
2 shared publications- Joanna Waczyńska
Jagiellonian University
2 shared publications
Latest Publications
- 27 June 2026
- Published by Springer Nature
- p. 386-394
MeshSplats: Mesh-Based Rendering with Gaussian Splatting Initialization
- 27 June 2026
- Published by Springer Nature
- p. 386-394
MeshSplats: Mesh-Based Rendering with Gaussian Splatting Initialization
- 27 June 2026
- Published by Springer Nature
- p. 575-582
HuSc3D: Human Sculpture Dataset for 3D Object Reconstruction
- 27 June 2026
- Published by Springer Nature
- p. 575-582
HuSc3D: Human Sculpture Dataset for 3D Object Reconstruction
- Top Cited Papers
- 11 February 2026
- Published by Elsevier in Computer Vision and Image Understanding
- Vol. 265
GASP: Gaussian Splatting for physics-based simulations
- 11 February 2026
- Published by Elsevier in Computer Vision and Image Understanding
- Vol. 265
Top Cited PapersGASP: Gaussian Splatting for physics-based simulations
- 25 December 2025
- Published by Elsevier in Information Sciences
- Vol. 735
VeGaS: Video Gaussian Splatting
- 25 December 2025
- Published by Elsevier in Information Sciences
- Vol. 735
VeGaS: Video Gaussian Splatting
- Open Access
HuSc3D: Human Sculpture dataset for 3D object reconstruction
3D scene reconstruction from 2D images is one of the most important tasks in computer graphics. Unfortunately, existing datasets and benchmarks concentrate on idealized synthetic or meticulously captured realistic data. Such benchmarks fail to convey the inherent complexities encountered in newly acquired real-world scenes. In such scenes especially those acquired outside, the background is often dynamic, and by popular usage of cell phone cameras, there might be discrepancies in, e.g., white balance. To address this gap, we present HuSc3D, a novel dataset specifically designed for rigorous benchmarking of 3D reconstruction models under realistic acquisition challenges. Our dataset uniquely features six highly detailed, fully white sculptures characterized by intricate perforations and minimal textural and color variation. Furthermore, the number of images per scene varies significantly, introducing the additional challenge of limited training data for some instances alongside scenes with a standard number of views. By evaluating popular 3D reconstruction methods on this diverse dataset, we demonstrate the distinctiveness of HuSc3D in effectively differentiating model performance, particularly highlighting the sensitivity of methods to fine geometric details, color ambiguity, and varying data availability--limitations often masked by more conventional datasets.
Open AccessHuSc3D: Human Sculpture dataset for 3D object reconstruction
3D scene reconstruction from 2D images is one of the most important tasks in computer graphics. Unfortunately, existing datasets and benchmarks concentrate on idealized synthetic or meticulously captured realistic data. Such benchmarks fail to convey the inherent complexities encountered in newly acquired real-world scenes. In such scenes especially those acquired outside, the background is often dynamic, and by popular usage of cell phone cameras, there might be discrepancies in, e.g., white balance. To address this gap, we present HuSc3D, a novel dataset specifically designed for rigorous benchmarking of 3D reconstruction models under realistic acquisition challenges. Our dataset uniquely features six highly detailed, fully white sculptures characterized by intricate perforations and minimal textural and color variation. Furthermore, the number of images per scene varies significantly, introducing the additional challenge of limited training data for some instances alongside scenes with a standard number of views. By evaluating popular 3D reconstruction methods on this diverse dataset, we demonstrate the distinctiveness of HuSc3D in effectively differentiating model performance, particularly highlighting the sensitivity of methods to fine geometric details, color ambiguity, and varying data availability--limitations often masked by more conventional datasets.
- 25 December 2024
- Published by Elsevier in Computer Vision and Image Understanding
- Vol. 251
Gaussian Splatting with NeRF-based color and opacity
- 25 December 2024
- Published by Elsevier in Computer Vision and Image Understanding
- Vol. 251
Gaussian Splatting with NeRF-based color and opacity
- Open Access
VeGaS: Video Gaussian Splatting
Implicit Neural Representations (INRs) employ neural networks to approximate discrete data as continuous functions. In the context of video data, such models can be utilized to transform the coordinates of pixel locations along with frame occurrence times (or indices) into RGB color values. Although INRs facilitate effective compression, they are unsuitable for editing purposes. One potential solution is to use a 3D Gaussian Splatting (3DGS) based model, such as the Video Gaussian Representation (VGR), which is capable of encoding video as a multitude of 3D Gaussians and is applicable for numerous video processing operations, including editing. Nevertheless, in this case, the capacity for modification is constrained to a limited set of basic transformations. To address this issue, we introduce the Video Gaussian Splatting (VeGaS) model, which enables realistic modifications of video data. To construct VeGaS, we propose a novel family of Folded-Gaussian distributions designed to capture nonlinear dynamics in a video stream and model consecutive frames by 2D Gaussians obtained as respective conditional distributions. Our experiments demonstrate that VeGaS outperforms state-of-the-art solutions in frame reconstruction tasks and allows realistic modifications of video data. The code is available at: https://github.com/gmum/VeGaS.
Open AccessVeGaS: Video Gaussian Splatting
Implicit Neural Representations (INRs) employ neural networks to approximate discrete data as continuous functions. In the context of video data, such models can be utilized to transform the coordinates of pixel locations along with frame occurrence times (or indices) into RGB color values. Although INRs facilitate effective compression, they are unsuitable for editing purposes. One potential solution is to use a 3D Gaussian Splatting (3DGS) based model, such as the Video Gaussian Representation (VGR), which is capable of encoding video as a multitude of 3D Gaussians and is applicable for numerous video processing operations, including editing. Nevertheless, in this case, the capacity for modification is constrained to a limited set of basic transformations. To address this issue, we introduce the Video Gaussian Splatting (VeGaS) model, which enables realistic modifications of video data. To construct VeGaS, we propose a novel family of Folded-Gaussian distributions designed to capture nonlinear dynamics in a video stream and model consecutive frames by 2D Gaussians obtained as respective conditional distributions. Our experiments demonstrate that VeGaS outperforms state-of-the-art solutions in frame reconstruction tasks and allows realistic modifications of video data. The code is available at: https://github.com/gmum/VeGaS.