Exploring User Experiences with Generative AI-Reconstructed Daily Photos
Authors
The potential of generative AI in daily photo documentation lies in its ability to support the creation of more meaningful records by reconstructing daily photos in ways that vividly capture users' experiences. Building on this potential, we aimed to explore the new experiences that could emerge through the reconstruction of daily photos. We asked 12 participants to take photos of their daily lives and write text narratives over a 10- to 20-day period. Using these photos and narratives, we generated various reconstructed images, which were then used as materials for participant interviews. Our findings revealed that reconstructed images fostered reflective documentation experiences by (1) expanding narratives about experiences, (2) helping participants discover moments they genuinely wanted to record, (3) organizing their thoughts about their experiences, and (4) enhancing their awareness of personal identity. Additionally, we identified considerations for transforming daily photos. Based on these findings, we conclude by discussing the role of generative AI in enhancing reflective photographic practices.
Research Questions / Practical Problems
Question signals indexed for this paper.
- 100%
PANDALens: Towards AI-Assisted In-Context Writing on OHMD During Travels
CHI '24· Generative AI (Text, Image, Music, Video) +1
- 67%
Integrating Machine Learning Data with Symbolic Knowledge from Collaboration Practices of Curators to Improve Conversational Systems
CHI '21· Conversational Chatbots +2
- 67%
Rambler: Supporting Writing With Speech via LLM-Assisted Gist Manipulation
CHI '24· Voice User Interface (VUI) Design +2
- 67%
User Experience Design Professionals’ Perceptions of Generative Artificial Intelligence
CHI '24· Generative AI (Text, Image, Music, Video) +1
- 67%
Thoughtful, Confused, or Untrustworthy: How Text Presentation Influences Perceptions of AI Writing Tools
C&C '25· Generative AI (Text, Image, Music, Video) +2
- 67%
How People Prompt Generative AI to Create Interactive VR Scenes
DIS '24· Social & Collaborative VR +2
- 67%
Better Together? An Evaluation of AI-Supported Code Translation
IUI '22· Generative AI (Text, Image, Music, Video) +1
- 67%
Patchview: LLM-powered Worldbuilding with Generative Dust and Magnet Visualization
UIST '24· Generative AI (Text, Image, Music, Video) +1
Based on Jaccard similarity of research subtopics & professions (≥60%)