Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 17, 2025Advanced Intelligent SystemsOpen Access

Memory‐Reduced Convolutional Neural Network for Fast Phase Hologram Generation

View Full Paper
Ask AI
Bookmark
Share

Authors

CCChenliang ChangUniversity of Shanghai for Science and TechnologyCZChuang ZhaoBeihua UniversityBDBo DaiKalasalingam Academy of Research and Education

Discussion

Loading...

Member takes

Implication

Novel approach generates 3D holograms using a low-resource convolutional neural network, suggesting improved efficiency for virtual reality displays.

Key Points

  • The INT8 model reduces size by 60%, enhancing efficiency for holographic computation, critical for mobile platforms.
  • Processing speed improves by three times while achieving similar hologram quality compared to the original FP32 model.
  • The proposed model addresses the limitations of high computational costs, enabling better deployment in human-centric applications.
  • This work bridges the gap between advanced holographic computation and practical wearable display systems in virtual reality.

Cite This Study

Chang et al. (2025) studied this question.

synapsesocial.com/papers/68d4604731b076d99fa5f70ehttps://doi.org/10.1002/aisy.202500354
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Near‐Eye Display and Tracking Technologies for Virtual and Augmented Reality2019 · 223 citations
  2. 2From picture to 3D hologram: end-to-end learning of real-time 3D photorealistic hologram generation from 2D image input2023 · 31 citations
  3. 3Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference2018 · 3,967 citations
  4. 4Recent advances in holographic recording media for dynamic holographic display2014 · 29 citations
  5. 5Projection-type see-through holographic three-dimensional display2016 · 321 citations