A Lightweight Complex-Valued Deformable CNN for High-Quality Computer-Generated Holography
This work addresses the problem of improving holographic display quality for virtual and augmented reality applications, representing an incremental advance by optimizing feature extraction in deep learning-based methods.
The paper tackles the challenge of accurately modeling the diffraction process in computer-generated holography by introducing a complex-valued deformable CNN that dynamically adjusts the convolution kernel's shape to enhance the effective receptive field, achieving state-of-the-art performance with a peak signal-to-noise ratio up to 9.71 dB higher than existing models and using only about one-eighth the parameters of a leading baseline.
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.