High-Quality Depth-Adaptive Computer-Generated Hologram Using Depth-aware Plug-in Network.

Learning-based computer-generated holography (CGH) enables real-time hologram generation, but many existing methods are trained for a fixed propagation depth and require retraining when the target depth changes. Recent depth-adaptive approaches alleviate this limitation, yet often rely on specially designed architectures, limiting compatibility with existing CGH networks. We propose a depth-aware plug-in network that equips existing fixed-depth CGH models with depth-adaptive generation capability without modifying their backbones. The module performs intermediate feature modulation using a physics-guided signal derived from the optical transfer function (OTF), which captures propagation-dependent phase structures for effective depth adaptation. By decoupling depth modeling from network design, the proposed method can be flexibly integrated into diverse CGH frameworks with minimal overhead while avoiding the need for separate models at different propagation depths, thereby reducing the overall training cost. Experiments on multiple representative CGH backbones, together with ablation studies and optical validations, demonstrate consistently improved reconstruction quality and robust depth generalization across a wide range of propagation depths, offering a practical solution for generalizable depth-adaptive CGH systems .