轻量级复数可变形卷积提升全息图像生成质量
A Lightweight Complex-Valued Deformable CNN for High-Quality Computer-Generated Holography
- 引入复数可变形卷积，动态调整感受野以更好捕捉衍射信息
- 在1920×1072分辨率下，峰值信噪比分别高出现有模型2.04~9.71dB
- 参数量仅为CCNN-CGH的1/8，适合部署于资源受限设备
全息显示在虚拟现实与增强现实中有重要潜力，因其能提供完整的深度线索。基于深度学习的计算全息（CGH）方法发挥关键作用。在衍射过程中，每个像素均影响重建图像，但此前工作难以充分建模该过程，主要受限于有效感受野（ERF）不足。本文设计了复数可变形卷积并集成至网络，通过动态调整卷积核形状，增强ERF灵活性，实现更优特征提取。该方法仅用单一模型即在模拟与光学实验中均达到当前最优性能，显著优于现有开源模型。具体而言，在1920×1072分辨率下，其峰值信噪比分别比CCNN-CGH、HoloNet和Holo-encoder高出2.04 dB、5.31 dB和9.71 dB。模型参数量约为CCNN-CGH的八分之一。
原文摘要 · Abstract (English)
Holographic displays have significant potential in virtual reality and augmented reality owing to their ability to provide all the depth cues. Deep learning-based methods play an important role in computer-generated holography (CGH). During the diffraction process, each pixel exerts an influence on the reconstructed image. However, previous works face challenges in capturing sufficient information to accurately model this process, primarily due to the inadequacy of their effective receptive field (ERF). Here, we designed complex-valued deformable convolution for integration into network, enabling dynamic adjustment of the convolution kernel's shape to increase flexibility of ERF for better feature extraction. This approach allows us to utilize a single model while achieving state-of-the-art performance in both simulated and optical experiment reconstructions, surpassing existing open-source models. Specifically, our method has a peak signal-to-noise ratio that is 2.04 dB, 5.31 dB, and 9.71 dB higher than that of CCNN-CGH, HoloNet, and Holo-encoder, respectively, when the resolution is 1920$\times$1072. The number of parameters of our model is only about one-eighth of that of CCNN-CGH.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。