How people see
your photographs
A free photo analysis tool that produces an attention heatmap and predicted scanpath for any image you upload, showing where viewers' eyes are likely to gather and how they move through the frame. Built for photographers, artists, and anyone curious about visual attention in their own work.
Preset guide
- General
- Balanced mode for most photographs.
- Portraits
- Designed for portraits with a clear, visible face. Use General when faces are mostly hidden, masked, or strongly occluded.
- Nature
- Designed for landscapes, where attention tends to move across the wider frame.
Advanced settings
Heatmap
The attention heatmap shows where visual attention is most likely to gather in the frame.
Based on human attention data.
Scanpath
The scanpath shows the likely sequence of eye fixations as a viewer's gaze moves through the photograph.
Based on real eye-tracking research.
Privacy
Images you upload are analysed only to produce your heatmap and scanpath. They are not stored.
For more details, see the Privacy page.
Support PhotoSalience
If this tool helped you read your image differently, you can support the project and its continued development.
DonateAbout
PhotoSalience is a project by photographer Martin Kocjan exploring the meeting point between composition and human attention, and the way vision-science models can help reveal it.
Follow the work on Instagram
Get in touch
photosalience@gmail.com Copied
Research Credits
PhotoSalience draws on the following saliency and scanpath models:
- UNISAL Droste, R., Jiao, J., & Noble, J. A. (2020). Unified Image and Video Saliency Modeling. In Proceedings of the 16th European Conference on Computer Vision (ECCV).
- DeepGaze III Kümmerer, M., Bethge, M., & Wallis, T. S. A. (2022). DeepGaze III: Modeling free-viewing human scanpaths with deep learning. Journal of Vision, 22(5), 7.