Test Dataset of AI Altered Images for Photogrammetric Reconstruction
<p>As a part of a test of the capability of using AI altered images in photogrammetry, I generated these image sets using the Prisma AI app. All of these datasets will result in a model in Agisoft Metashape. Prisma AI acts as a filter, changing an input image to the style of another artwork. </p> <p>Original images were collected using a Samsung S22 camera on the 1x zoom rear lens. The subject is a rock decoration in the Utrecht University Botanical Garden.</p> <p>Results can be seen on Sketchfab: https://sketchfab.com/gspeed0689/collections/prisma-photogrammetry-2e334a36c6e942798370d594de5e6f0c </p> <p>Included datasets:</p> <ul> <li>true-color.zip - The original images from the Samsung S22</li> <li>aviator-lowres - Processed images at normal (low resolution) quality with the filter labelled Aviator</li> <li>bubblegum-lowres - Processed images at normal (low resolution) quality with the filter labelled Bubblegum</li> <li>gothic-lowres - Processed images at normal (low resolution) quality with the filter labelled Gothic</li> <li>gothic-hd.zip - Processed images at HD (paid subscription required) quality with the filter labelled Gothic</li> <li>true-color.fbx - 3D model created with Agisoft Metashape using the parameters listed below and the images from true-color.zip</li> <li>aviator-lowres.fbx - 3D model created with Agisoft Metashape using the parameters listed below and the images from aviator-lowres.zip</li> <li>bubblegum-lowres.fbx - 3D model created with Agisoft Metashape using the parameters listed below and the images from bubblegum-lowres.zip</li> <li>gothic-lowres.fbx - 3D model created with Agisoft Metashape using the parameters listed below and the images from gothic-lowres.zip</li> <li>gothic-hd.fbx - 3D model created with Agisoft Metashape using the parameters listed below and the images from gothic-hd.zip</li> </ul> <p>Processing parameters in Agisoft Metashape v 1.7:</p> <ul> <li>Alignment defaults</li> <li>Dense cloud creation at "High" quality</li> <li>Mesh defaults</li> </ul>
ShareScore
40/100
Overall dataset sharing score
Score breakdown
These five areas show where the dataset supports — or may limit — practical reuse.
- Stewardship
- 8
- Harmonization
- 4
- Access
- 16
- Reuse readiness
- 8
- Engagement
- 4