CV-HoloSR uses a complex-valued residual dense network, depth-aware perceptual loss, and complex LoRA fine-tuning to perform hologram super-resolution for volumetric upsampling, achieving 32% better LPIPS while maintaining physical depth consistency.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
ZRNet uses a Zernike Graph module modeling azimuthal relationships and a Frequency-Aware Alignment loss to jointly predict aberration coefficients and restore images, reporting state-of-the-art results on CytoImageNet and real PSF data.
citing papers explorer
-
CV-HoloSR: Hologram to hologram super-resolution through volume-upsampling three-dimensional scenes
CV-HoloSR uses a complex-valued residual dense network, depth-aware perceptual loss, and complex LoRA fine-tuning to perform hologram super-resolution for volumetric upsampling, achieving 32% better LPIPS while maintaining physical depth consistency.
-
Physics-Informed Graph Neural Networks for Frequency-Aware Optical Aberration Correction
ZRNet uses a Zernike Graph module modeling azimuthal relationships and a Frequency-Aware Alignment loss to jointly predict aberration coefficients and restore images, reporting state-of-the-art results on CytoImageNet and real PSF data.