ART3mis is a general-purpose, user-friendly, interactive web-based annotation tool for 3D objects, which is primarily attuned to aid cultural heritage conservators, restorers, and curators in easily handling, segmenting, and annotating 3D digital replicas of artefacts, without requiring any technical skills in 3D imaging and graphics. It is also a significant tool for the manual annotation of 3D objects, and the creation of ground-truth datasets for machine learning applications.
The main purpose of ART3mis is to provide people with no expertise or technical skills in 3D imaging and graphics, a simple, user-friendly, interactive annotation application for segmenting and annotating 3D objects.
At the same time, it is rather useful dataset formation tool for 3D image research and applications.
ART3mis works by using a direct-on-surface annotation approach, providing various ways of selecting a Region of Interest (ROI) on an object’s 3D model surface, and attaching textual annotations.
There may be single or multiple annotations per 3D object and the process can be repeated to add, edit or delete annotations. The annotations are stored as data structures in a user friendly and machine-readable format enabling interoperability, namely the JSON standard.
Currently, two modes of ROI selection are supported: (a) brush or painting selection; and (b) polyline or lasso selection, although other approaches are under investigation and development.
The core advantage of ART3mis is that it’s a cross-platform, easy to use, WYSIWYG, 3D web application, which everyone can use regardless of their operating system. Even though web applications usually have access to limited computing resources, ART3mis can handle large 3D models easily.
Through a minimalistic and simple design, ART3mis provides a user-friendly environment with easy-to-use controls.
Easy integration and interoperability are core ART3mis attributes. Other systems can easily import the annotations produced by ART3mis as they are stored in the standard JSON format that enables data interchange among Web-connected systems.
ART3mis supports many common 3D object file formats from various 3D imaging and computer graphic platforms, such as Blender, MeshLab, as well as 3D models from 3D digitization projects.
Support of non-technical users is a key aspect of ART3mis. It was implemented based on the WYSIWYG philosophy, and a user-friendly environment with easy-to-use controls is provided.
The web character of ART3mis provides portability, as it is accessible by any typical computer system with a browser and an internet connection.
ART3mis is primarily attuned to aid cultural heritage practitioners, conservators, restorers, and curators, with no technical skills in 3D imaging and graphics, in easily annotating 3D digitized artefacts.
In addition, ART3mis serves as a dataset annotation tool for 3D imaging research primarily targeting the engineering and computer science research community.
First of all, we would like to thank you for your availability to collaborate in a study designed by researchers from the WARMEST´S project.
Your participation will be essential for the success of this work. Specifically, we would like you to answer honestly a series of questions about your experience with your volunteer tourism program. The estimated duration of the survey is about 10 minutes.
Remember that there are no correct answers and that your sincerity is essential to guarantee the rigor of the investigation.
The information you voluntarily provide and the data collected is completely anonymous and will be analyzed in an aggregated manner to carry out statistical analysis for scientific research purposes.
Kind regards and thanks again!
This survey is anonymous.
The record of your survey responses does not contain any identifying information about you, unless a specific survey question explicitly asked for it.
If you used an identifying token to access this survey, please rest assured that this token will not be stored together with your responses. It is managed in a separate database and will only be updated to indicate whether you did (or did not) complete this survey. There is no way of matching identification tokens with survey responses.