Entangled Gazes: Reconstituting the Stereoscopic Box Set with LLMs and Virtual Reality

  • Paul Heinrich Bethge*
  • , Emmanuelle Denove
  • , Dhruva Gowda-Storz
  • , Adriano Viegas Milani
  • , Tai Leong Cheong
  • , Paul Bourke
  • , Sarah Kenderdine
  • , Jeffrey Shaw
  • *Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

Abstract

This paper presents a computational framework for critically reinterpreting colonial-era stereoscopic box sets. Using James Ricalton's China through the Stereoscope (1901) as a case study, we deconstruct its linear narrative using NLP methods for thematic modeling, semantic mapping, and colonial language identification. This analysis informs two complementary artworks in a large-scale 360° VR environment. Cross Eyed offers a guided experience, using the thematic models as lenses for inquiry and visually distinguishing identified rhetoric. Latent Cartographies, in contrast, empowers users to freely navigate the archive's raw semantic space, fostering diverse modes of experiential engagement with contested heritage. For demonstration visit: https://epfl-emplus.github.io/EntangledGazes/

Original languageEnglish
Title of host publicationSA Art Papers '25: Proceedings of the SIGGRAPH Asia 2025 Art Papers
EditorsStephen N. Spencer, Taku Komura, Kian Peng Ong
PublisherAssociation for Computing Machinery (ACM)
Pages1-5
Number of pages5
ISBN (Print)9798400721298
DOIs
Publication statusPublished - 14 Dec 2025
Event2025 SIGGRAPH Asia 2025 Art Papers, SA 2025 - Hong Kong, Hong Kong, China
Duration: 15 Dec 202518 Dec 2025

Publication series

NameProceedings - SIGGRAPH Asia 2025 Art Papers, SA 2025

Conference

Conference2025 SIGGRAPH Asia 2025 Art Papers, SA 2025
Country/TerritoryHong Kong, China
CityHong Kong
Period15/12/2518/12/25

User-Defined Keywords

  • Archival Art
  • NLP Methods for Art
  • Stereoscopic Photography
  • Virtual Reality

Fingerprint

Dive into the research topics of 'Entangled Gazes: Reconstituting the Stereoscopic Box Set with LLMs and Virtual Reality'. Together they form a unique fingerprint.

Cite this