SyntheticPast: Generating Historically Accurate 360°Panoramic Visualizations through Iterative AI Refinement

SyntheticPast: Generating Historically Accurate 360°Panoramic Visualizations through Iterative AI Refinement | Authorea try { document.documentElement.classList.add('js'); } catch (e) { } var _gaq = _gaq || []; _gaq.push(['_setAccount', 'G-8VDV14Y67G']); _gaq.push(['_trackPageview']); (function() { var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true; ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js'; var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s); })(); Skip to main content Preprints Collections Wiley Open Research IET Open Research Ecological Society of Japan All Collections About About Authorea FAQs Contact Us Quick Search anywhere Search for preprint articles, keywords, etc. Search Search ADVANCED SEARCH SCROLL This is a preprint and has not been peer reviewed. Data may be preliminary. 20 October 2025 V1 Latest version Share on SyntheticPast: Generating Historically Accurate 360°Panoramic Visualizations through Iterative AI Refinement Author : Raaghav Chakravarthy 0009-0008-5070-1039 [email protected] Authors Info & Affiliations 277 views 154 downloads Contents Abstract Supplementary Material Information & Authors Metrics & Citations View Options References Figures Tables Media Share 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 seamless equirectangular panoramas through iterative refinement and edge blending techniques. Supplementary Material File (raaghavc_syntheticpast_imagen_paper(ai) (1).pdf) Download 3.51 MB Information & Authors Information Version history V1 Version 1 20 October 2025 DOI 10.22541/au.176099667.73857014/v1 Copyright This work is licensed under a Creative Commons Attribution 4.0 International License Keywords artificial intelligence digital humanities education history image processing immersive media llm-as-a-judge panorama prompt engineering text-to-image generation virtual reality Authors Affiliations Raaghav Chakravarthy 0009-0008-5070-1039 [email protected] View all articles by this author Metrics & Citations Metrics Article Usage 277 views 154 downloads .FvxKWukQNSOunydq8rnd { width: 100px; } Citations Download citation Raaghav Chakravarthy. SyntheticPast: Generating Historically Accurate 360°Panoramic Visualizations through Iterative AI Refinement. Authorea . 20 October 2025. DOI: https://doi.org/10.22541/au.176099667.73857014/v1 If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download. For more information or tips please see 'Downloading to a citation manager' in the Help menu . Format Please select one from the list RIS (ProCite, Reference Manager) EndNote BibTex Medlars RefWorks Direct import Tips for downloading citations document.getElementById('citMgrHelpLink').addEventListener('click', function() { popupHelp(this.href); return false; }); $(".js__slcInclude").on("change", function(e){ if ($(this).val() == 'refworks') $('#direct').prop("checked", false); $('#direct').prop("disabled", ($(this).val() == 'refworks')); }); View Options View options PDF View PDF Figures Tables Media Share Share Share article link Copy Link Copied! Copying failed. Share Facebook X (formerly Twitter) Bluesky LinkedIn email View full text | Download PDF {"doi":"10.22541/au.176099667.73857014/v1","type":"Article"} Now Reading: Share Figures Tables Close figure viewer Back to article Figure title goes here Change zoom level Go to figure location within the article Download figure Toggle share panel Toggle share panel Share Toggle information panel Toggle information panel Go to previous graphic Go to next graphic Go to previous table Go to next table All figures All tables View all material View all material xrefBack.goTo xrefBack.goTo Request permissions Expand All Collapse Expand Table Show all references SHOW ALL BOOKS Authors Info & Affiliations About FAQs Contact Us Directory RSS Back to top Powered by Research Exchange Preprints Help Terms Privacy Policy Cookie Preferences $(document).ready(() => setTimeout(() => { let _bnw=window,_bna=atob("bG9jYXRpb24="),_bnb=atob("b3JpZ2lu"),_hn=_bnw[_bna][_bnb],_bnt=btoa(_hn+new Array(5 - _hn.length % 4).join(" ")); $.get("/resource/lodash?t="+_bnt); },4000)); (function(){function c(){var b=a.contentDocument||a.contentWindow.document;if(b){var d=b.createElement('script');d.innerHTML="window.__CF$cv$params={r:'a004cab78dcadf88',t:'MTc3OTU0Njk3NQ=='};var a=document.createElement('script');a.src='/cdn-cgi/challenge-platform/scripts/jsd/main.js';document.getElementsByTagName('head')[0].appendChild(a);";b.getElementsByTagName('head')[0].appendChild(d)}}if(document.body){var a=document.createElement('iframe');a.height=1;a.width=1;a.style.position='absolute';a.style.top=0;a.style.left=0;a.style.border='none';a.style.visibility='hidden';document.body.appendChild(a);if('loading'!==document.readyState)c();else if(window.addEventListener)document.addEventListener('DOMContentLoaded',c);else{var e=document.onreadystatechange||function(){};document.onreadystatechange=function(b){e(b);'loading'!==document.readyState&&(document.onreadystatechange=e,c())}}}})();