SyntheticPast: Generating Historically Accurate 360°Panoramic Visualizations through Iterative AI Refinement
Abstract
This paper presents SyntheticPast, a novel framework for generating historically accurate 360°panoramic visualizations of past events by integrating Large Language Models (LLMs) with image generation models. Traditional history education relies heavily on text-based resources, limiting students' ability to engage with and contextualize historical events. The proposed approach combines GPT-4o with Stable Diffusion through an iterative prompt refinement pipeline that incorporates primary source data and includes historical accuracy verification. A multi-stage generation process is introduced where GPT-4o both evaluates generated panoramas for historical accuracy and refines prompts to improve subsequent generations. This system was successfully implemented for reconstructing 1850s San Francisco during the California Gold Rush, using primary sources including travelogs and eyewitness accounts. The results demonstrate that AI-driven iterative refinement can produce historically grounded, immersive 360°visualizations suitable for educational applications. The system achieved an average historical accuracy score of 81.7% with 62.5% of generated panoramas meeting the 85% threshold. A Retrieval Augmented Generation (RAG) chatbot was also developed that provides contextual information about the visualizations, creating an interactive educational experience. This work establishes a practical framework for AI-augmented historical education and demonstrates the viability of generating…
Read the paper
Related studies
- Learning from First-Generation Qualitative Approaches in the IS Discipline: An Evolutionary View and Some Implications for Authors and Evaluators (PART 1/2)
- Commentary on the clinical and preclinical dosage limits of interstitially administered magnetic fluids for therapeutic hyperthermia based on current practice and efficacy models
- Prosthesis: New Technological Opportunities and Innovative Biomedical Devices
- The history and future of neural modeling for cochlear implants
- Ryanodine receptors: waking up from refractoriness
- Novel Transgenic Rabbit Model Sheds Light on the Puzzling Role of Matrix Metalloproteinase-12 in Atherosclerosis
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.