1. [Publications](/publications)
2. Assessing Learned Models for Phase-only Hologram Compression
 
 # Assessing Learned Models for Phase-only Hologram Compression

  ![](/sites/default/files/styles/wide/public/publications/siggraphposters25-25-fig1.jpg?itok=vY9HmGyj)

 We evaluate the performance of four common learned models utilizing INR and VAE structures for compressing phase-only holograms in holographic displays. The evaluated models include a **vanilla MLP**, **SIREN** \[Sitzmann et al. [2020](https://dl.acm.org/doi/10.1145/3721250.3742993#core-collateral-Bib0004)\], and **FilmSIREN** \[Chan et al. [2021](https://dl.acm.org/doi/10.1145/3721250.3742993#core-collateral-Bib0002)\], with **TAESD** \[Bohan [2023](https://dl.acm.org/doi/10.1145/3721250.3742993#core-collateral-Bib0001)\] as the representative VAE model. Our experiments reveal that a pretrained image VAE, **TAESD**, with 2.2*M* parameters struggles with phase-only hologram compression, revealing the need for task-specific adaptations. Among the INR s, **SIREN** with 4.9*k* parameters achieves compression with high quality in the reconstructed 3D images (PSNR = 34.54 dB). These results emphasize the effectiveness of INR s and identify the limitations of pretrained image compression VAE s for hologram compression task.



 ## Authors



Zicong Peng (University College London)

Yicheng Zhan (University College London)

[Josef Spjut](/person/josef-spjut)

Kaan Akşit (University College London)

 

 

 ## Publication Date



Sunday, August 10, 2025

 

 ## Published in



[SIGGRAPH 2025 Posters](https://dl.acm.org/doi/10.1145/3721250.3742993)

 

 ## Research Area



[Artificial Intelligence and Machine Learning ](/research-area/machine-learning-artificial-intelligence)

[Computer Graphics](/research-area/computer-graphics)

[Generative AI](/research-area/generative-ai)

[VR, AR and Display Technology](/research-area/virtual-augmented-reality)

 

 

 ## External Links



[Project Page](https://complightlab.com/publications/assess_hologram_compression/)

[Manuscript](https://www.kaanaksit.com/assets/pdf/PengEtAl_SIGGRAPH2025_Assessing_learned_models_for_phase_only_hologram_compression.pdf)

[Poster](https://www.kaanaksit.com/assets/pdf/PengEtAl_SIGGRAPH2025_Poster_assessing_learned_models_for_phase_only_hologram_compression.pdf)

[arxiv](https://arxiv.org/abs/2507.06646)

[doi](https://doi.org/10.1145/3721250.3742993)