MemoryDiorama: Generating Dynamic 3D Diorama from Everyday Photos for Memory Recall

2026-04-08

AI Summary

This work addresses the limited efficacy of static photographs as memory cues by proposing an “Enhanced Memory Cues” framework that, for the first time, integrates large language models with 3D generative techniques to transform 2D images into dynamic, interactive 3D dioramas in mixed reality. The system leverages AI to automatically generate contextual information—encompassing scene understanding, spatial layout, object and human animations, and particle effects—to construct an immersive memory-supportive environment. User studies demonstrate that, compared to viewing photographs or static dioramas alone, this approach significantly enhances the retrieval of internal episodic details, perceptual richness, cue-related associations, and visual vividness, thereby validating the effectiveness of dynamically enriched contextual cues in supporting autobiographical memory.

Abstract

We present MemoryDiorama, a prototype system that introduces augmented memory cues, a concept that extends captured personal media with AI-generated contextual information to enhance autobiographical memory recall. MemoryDiorama transforms everyday photos into dynamic 3D dioramas in mixed reality by integrating LLM-based scene analysis with 3D object generation, animation, and spatial composition. The system extracts geographic information, object attributes, lighting conditions, and atmospheric elements from the photos. It then animates these elements with generative components such as object animations, human motion, geographical effects, and particle effects to provide richer cues for memory recall. We evaluated MemoryDiorama in a within-subject user study with 18 participants, comparing three conditions: Photo-Only, Static Diorama, and MemoryDiorama. Compared with both Photo-Only and Static Diorama, MemoryDiorama elicited more internal and in-cue details during recall. It also increased perceptual details and visual vividness ratings, suggesting richer recollective experience.

Problem

• autobiographical memory
• memory recall
• augmented memory cues
• personal media
• mixed reality

Innovation

• dynamic 3D diorama
• augmented memory cues
• LLM-based scene analysis
• generative animation
• mixed reality memory recall