Vident-lab: a dataset for multi-task video processing of phantom dental scenes

Description

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 an inter-frame homography matrix. The homography warps the current frame to the previous frame with respect to the teeth. Moreover, we provide the list of human-annotated segmentation masks so that future segmentation methods can adhere to our evaluation protocol and compare their results to MOST-Net in [1]. The remaining segmentation masks were obtained with HRNet48. The dataset has the training, validation, and test sets of 300, 29, and 80 videos, respectively.

If you use the Vident-lab dataset, please cite [1] that describes the dataset in detail.

[1] Efklidis Katsaros, Piotr K. Ostrowski, Krzysztof Wlodarczak, Emilia Lewandowska, Jacek Ruminski, Damian Siupka-Mroz, Lukasz Lassmann, Anna Jezierska, Daniel Wesierski. "Multi-task video enhancement for dental interventions" In International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, Cham, 2022.

Dataset file

Vident-lab.zip

21.2 GB, S3 ETag a997377bcd149b6c0a47688dd4af211b-43, downloads: 153

The file hash is calculated from the formula
hexmd5(md5(part1)+md5(part2)+...)-{parts_count} where a single part of the file is 512 MB in size.

Example script for calculation:
https://github.com/antespi/s3md5

download

File details

License:: open in new tab

CC BY-NC

Non-commercial

Details

Year of publication:

2022

Verification date:

2022-06-24

Dataset language:

English

Fields of science:

information and communication technology (Engineering and Technology)
biomedical engineering (Engineering and Technology)
Automation, electronic and electrical engineering (Engineering and Technology)

DOI:

10.34808/1jby-ay90

Verified by:

Gdańsk University of Technology

Keywords

References

Cite as

Authors

seen 1171 times

Search