Error-compensation network for ringing artifact reduction in holographic displays.

Recent advances in learning-based computer-generated holography (CGH) have unlocked novel possibilities for crafting phase-only holograms. However, existing approaches primarily focus on the learning ability of network modules, often neglecting the impact of diffraction propagation models. The resulting ringing artifacts, emanating from the Gibbs phenomenon in the propagation model, can degrade the quality of reconstructed holographic images. To this end, we explore a diffraction propagation error-compensation network that can be easily integrated into existing CGH methods. This network is designed to correct propagation errors by predicting residual values, thereby aligning the diffraction process closely with an ideal state and easing the learning burden of the network. Simulations and optical experiments demonstrate that our method, when applied to state-of-the-art HoloNet and CCNN, achieves PSNRs of up to 32.47 dB and 29.53 dB, respectively, surpassing baseline methods by 3.89 dB and 0.62 dB. Additionally, real-world experiments have confirmed a significant reduction in ringing artifacts. We envision this approach being applied to a variety of CGH algorithms, paving the way for improved holographic displays.