activity
20242026
collaborators

6 papers

cs.CV2026

X-Splat: Gaussian Splatting for 3D CBCT Generation from Single Panoramic Radiograph

Tomasz Szczepański, Szymon Płotka, Michal K. Grzeszczyk +2

Generating a 3D dental volume from a single panoramic radiograph (PXR) could provide a low-radiation alternative to Cone-Beam Computed Tomography (CBCT), but the problem is highly…

cs.CV2026

LumiMotion: Improving Gaussian Relighting with Scene Dynamics

Joanna Kaleta, Piotr Wójcik, Kacper Marzol +3

In 3D reconstruction, the problem of inverse rendering, namely recovering the illumination of the scene and the material properties, is fundamental. Existing Gaussian Splatting-bas…

eess.IV2025

GEPAR3D: Geometry Prior-Assisted Learning for 3D Tooth Segmentation

Tomasz Szczepański, Szymon Płotka, Michal K. Grzeszczyk +5

Tooth segmentation in Cone-Beam Computed Tomography (CBCT) remains challenging, especially for fine structures like root apices, which is critical for assessing root resorption in…

eess.IV2025

RegScore: Scoring Systems for Regression Tasks

Michal K. Grzeszczyk, Tomasz Szczepański, Pawel Renc +4

Scoring systems are widely adopted in medical applications for their inherent simplicity and transparency, particularly for classification tasks involving tabular data. In this wor…

eess.IV2024

TabMixer: Noninvasive Estimation of the Mean Pulmonary Artery Pressure via Imaging and Tabular Data Mixing

Michal K. Grzeszczyk, Przemysław Korzeniowski, Samer Alabed +3

Right Heart Catheterization is a gold standard procedure for diagnosing Pulmonary Hypertension by measuring mean Pulmonary Artery Pressure (mPAP). It is invasive, costly, time-cons…

eess.IV2024

Let Me DeCode You: Decoder Conditioning with Tabular Data

Tomasz Szczepański, Michal K. Grzeszczyk, Szymon Płotka +5

Training deep neural networks for 3D segmentation tasks can be challenging, often requiring efficient and effective strategies to improve model performance. In this study, we intro…