Skip to content
DraconiticResearch
Search Sources API
203,948 studies31 sourcesUpdated 10 min ago
Peer-reviewedCC BY 4.0PLOS One

A visual perception-guided framework for camera path planning in large-scale digital twin and AI-generated 3D scenes

  • Yan Zhang1
  • Wei Chen1
  • Gang Yang2
  1. 1Arts and Media School, Century College, Beijing University of Posts and Telecommunications, Beijing, China
  2. 2School of Information Science & Technology, Beijing Forestry University, Beijing, China
Open at sourcePDFDOICite

Abstract

This study investigates visual, cognitive, and spatial saliency indicators of architectural landmarks in large-scale ancient city ruins and digital twin virtual environments. It further examines users’ cognitive demands during pathfinding in large, complex environments and explores how different exploration strategies interact with interact with architectural spatial layouts. We propose a virtual camera exploration method guided by visual perception principles. Comparative experiments with several representative path optimization algorithms show that the proposed method outperforms existing methods and provides effective optimization strategies. This method identifies visually engaging and aesthetically rich regions in large-scale, complex virtual environments. As a result, it improves users’ exploration efficiency in such environments with multiple layers and complex structures, while enhancing their scene understanding and aesthetic experience. The proposed method has substantial practical value across multiple fields, including landscape animation, 3D heritage simulation, and virtual cultural tourism.

Related

  1. High-dimensional population codes reveal interpretable and diverse features underlying visual perception
    H. Issa, S. Liu, J. Balle +1
    bioRxivPreprintAll rights reservedFull textNeurosciencebioRxiv
  2. Repeated visual adaptation induces persistent behavioral and neural biases in body size perception
    Xiaohui Sang, Xue Dong, Min Bao
    iSciencePeer-reviewedCC BY-NC-ND 4.0Full textNeuroscienceCell PressCrossrefEurope PMC
  3. A Bio-Plausible Visual Neural Network for Locust-Inspired Collision Perception
    Qinbing Fu, Jiani Li, Jiajun Huang +1
    arXivPreprintCC BY-NC-ND 4.0Full textNeurosciencearXiv
  4. Perception of visual noise patterns depends on correlations produced in V1: A simulation study.
    Shaozhi Nie, Samantha A Montoya, Michael-Paul Schallmo +1
    Journal of visionPeer-reviewedCC BYFull textNeuroscienceEurope PMC
  5. Visual perception and color discrimination of the Asian citrus psyllid
    Sandra A Allan, Emma N I Weeks
    PLOS OnePeer-reviewedCC0Full textCell biologyNeurosciencePLOSEurope PMCPMC

Cite

BibTeXRIS
BibTeX
@article{zhang2026visual,
  title = {{A visual perception-guided framework for camera path planning in large-scale digital twin and AI-generated 3D scenes}},
  author = {Yan Zhang and Wei Chen and Gang Yang},
  journal = {PLOS One},
  year = {2026},
  month = sep,
  doi = {10.1371/journal.pone.0346542},
  url = {https://doi.org/10.1371/journal.pone.0346542},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - A visual perception-guided framework for camera path planning in large-scale digital twin and AI-generated 3D scenes
AU  - Yan Zhang
AU  - Wei Chen
AU  - Gang Yang
PY  - 2026
DA  - 2026/09/17
JO  - PLOS One
DO  - 10.1371/journal.pone.0346542
UR  - https://doi.org/10.1371/journal.pone.0346542
AB  - This study investigates visual, cognitive, and spatial saliency indicators of architectural landmarks in large-scale ancient city ruins and digital twin virtual environments. It further examines users’ cognitive demands during pathfinding in large, complex environments and explores how different exploration strategies interact with interact with architectural spatial layouts. We propose a virtual camera exploration method guided by visual perception principles. Comparative experiments with several representative path optimization algorithms show that the proposed method outperforms existing methods and provides effective optimization strategies. This method identifies visually engaging and aesthetically rich regions in large-scale, complex virtual environments. As a result, it improves users’ exploration efficiency in such environments with multiple layers and complex structures, while enhancing their scene understanding and aesthetic experience. The proposed method has substantial practical value across multiple fields, including landscape animation, 3D heritage simulation, and virtual cultural tourism.
SN  - 1932-6203
ER  -