CV-HoloSR: Hologram to hologram super-resolution through volume-upsampling three-dimensional scenes
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914466273165312 |
|---|---|
| author | No, Youchan Lee, Jaehong Choi, Daejun Park, Dae Youl Kim, Duksu |
| author_facet | No, Youchan Lee, Jaehong Choi, Daejun Park, Dae Youl Kim, Duksu |
| contents | Existing hologram super-resolution (HSR) methods primarily focus on angle-of-view expansion. Adapting them for volumetric spatial up-sampling introduces severe quadratic depth distortion, degrading 3D focal accuracy. We propose CV-HoloSR, a complex-valued HSR framework specifically designed to preserve physically consistent linear depth scaling during volume up-sampling. Built upon a Complex-Valued Residual Dense Network (CV-RDN) and optimized with a novel depth-aware perceptual reconstruction loss, our model effectively suppresses over-smoothing to recover sharp, high-frequency interference patterns. To support this, we introduce a comprehensive large-depth-range dataset with resolutions up to 4K. Furthermore, to overcome the inherent depth bias of pre-trained encoders when scaling to massive target volumes, we integrate a parameter-efficient fine-tuning strategy utilizing complex-valued Low-Rank Adaptation (LoRA). Extensive numerical and physical optical experiments demonstrate our method's superiority. CV-HoloSR achieves a 32% improvement in perceptual realism (LPIPS of 0.2001) over state-of-the-art baselines. Additionally, our tailored LoRA strategy requires merely 200 samples, reducing training time by over 75% (from 22.5 to 5.2 hours) while successfully adapting the pre-trained backbone to unseen depth ranges and novel display configurations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_10393 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CV-HoloSR: Hologram to hologram super-resolution through volume-upsampling three-dimensional scenes No, Youchan Lee, Jaehong Choi, Daejun Park, Dae Youl Kim, Duksu Graphics Optics Existing hologram super-resolution (HSR) methods primarily focus on angle-of-view expansion. Adapting them for volumetric spatial up-sampling introduces severe quadratic depth distortion, degrading 3D focal accuracy. We propose CV-HoloSR, a complex-valued HSR framework specifically designed to preserve physically consistent linear depth scaling during volume up-sampling. Built upon a Complex-Valued Residual Dense Network (CV-RDN) and optimized with a novel depth-aware perceptual reconstruction loss, our model effectively suppresses over-smoothing to recover sharp, high-frequency interference patterns. To support this, we introduce a comprehensive large-depth-range dataset with resolutions up to 4K. Furthermore, to overcome the inherent depth bias of pre-trained encoders when scaling to massive target volumes, we integrate a parameter-efficient fine-tuning strategy utilizing complex-valued Low-Rank Adaptation (LoRA). Extensive numerical and physical optical experiments demonstrate our method's superiority. CV-HoloSR achieves a 32% improvement in perceptual realism (LPIPS of 0.2001) over state-of-the-art baselines. Additionally, our tailored LoRA strategy requires merely 200 samples, reducing training time by over 75% (from 22.5 to 5.2 hours) while successfully adapting the pre-trained backbone to unseen depth ranges and novel display configurations. |
| title | CV-HoloSR: Hologram to hologram super-resolution through volume-upsampling three-dimensional scenes |
| topic | Graphics Optics |
| url | https://arxiv.org/abs/2604.10393 |