6 papers
X-Splat: Gaussian Splatting for 3D CBCT Generation from Single Panoramic Radiograph
Tomasz SzczepaÅski, Szymon PÅotka, 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…
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…
GEPAR3D: Geometry Prior-Assisted Learning for 3D Tooth Segmentation
Tomasz SzczepaÅski, Szymon PÅotka, 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…
RegScore: Scoring Systems for Regression Tasks
Michal K. Grzeszczyk, Tomasz SzczepaÅski, 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…
TabMixer: Noninvasive Estimation of the Mean Pulmonary Artery Pressure via Imaging and Tabular Data Mixing
Michal K. Grzeszczyk, PrzemysÅaw 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…
Let Me DeCode You: Decoder Conditioning with Tabular Data
Tomasz SzczepaÅski, Michal K. Grzeszczyk, Szymon PÅotka +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…