Daniel Węsierski - Research data

dr inż. Daniel Węsierski

Vident-synth: a synthetic intra-oral video dataset for optical flow estimation
Open Research Data
We introduce Vident-synth, a large dataset of synthetic dental videos with corresponding ground truth forward and backward optical flows and occlusion masks. It can be used for:
Vident-real: an intra-oral video dataset for multi-task learning
Open Research Data
- D. Węsierski
- A. Jezierska
- P. Kopa Ostrowski
- E. Lewandowska
- E. Katsaros
- A. Żółtowska
We introduce Vident-real, a large dataset of 100 video sequences of intra-oral scenes from real conservative dental treatments performed at the Medical University of Gdańsk, Poland. The dataset can be used for multi-task learning methods including:
SegSperm - a dataset of sperm images for blurry and small object segmentation
Open Research Data
- E. Lewandowska
- D. Węsierski
- M. Mazur-Milecka
- J. Liss
- A. Jezierska
Many deep learning applications require figure-ground segmentation. The performance of segmentation models varies across modalities and acquisition settings.
Vident-lab: a dataset for multi-task video processing of phantom dental scenes
Open Research Data
We introduce a new, asymmetrically annotated dataset of natural teeth in phantom scenes for multi-task video processing: restoration, teeth segmentation, and inter-frame homography estimation. Pairs of frames were acquired with a beam splitter. The dataset constitutes a low-quality frame, its high-quality counterpart, a teeth segmentation mask, and...

seen 2139 times