Assessing Learned Models for Phase-only Hologram Compression

2025/07/09 by Peng, Zicong, Zhan, Yicheng, Spjut, Josef +1 · 1 citation
#FOS: Computer and information sciences #Graphics (cs.GR)

paper · doi:10.48550/arxiv.2507.06646

Abstract

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, and FilmSIREN, with TAESD as the representative VAE model. Our experiments reveal that a pretrained image VAE, TAESD, with 2.2M parameters struggles with phase-only hologram compression, revealing the need for task-specific adaptations. Among the INRs, SIREN with 4.9k parameters achieves %40 compression with high quality in the reconstructed 3D images (PSNR = 34.54 dB). These results emphasize the effectiveness of INRs and identify the limitations of pretrained image compression VAEs for hologram compression task.

Citations

• Focal Surface Holographic Light Transport using Learned Spatially Adaptive Convolutions
• Multi-color Holograms Improve Brightness in Holographic Displays
• pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware\n Image Synthesis
• Implicit Neural Representations with Periodic Activation Functions

Cited by

• Complex-Valued 2D Gaussian Representation for Computer-Generated Holography

Related

• Compression of phase-only holograms with JPEG standard and deep learning
• Configurable Holography: Towards Display and Scene Adaptation
• A Large-Depth-Range Layer-Based Hologram Dataset for Machine Learning-Based 3D Computer-Generated Holography
• Real time computer generation of three-dimensional point cloud holograms through GPU implementation of compressed sensing Gerchberg-Saxton algorithm
• Divide-Conquer-and-Merge: Memory- and Time-Efficient Holographic Displays