Neural-Network-Enhanced Metalens Camera for High-Definition, Dynamic Imaging in the Long-Wave Infrared Spectrum
This provides a lightweight and cost-effective solution for high-definition dynamic imaging in the long-wave infrared spectrum, which is incremental as it enhances an existing metalens system with a neural network.
The paper tackles the problem of frequency loss in long-wave infrared imaging using a metalens camera by integrating a High-Frequency-Enhancing Cycle-GAN neural network, achieving dynamic imaging at 125 frames per second with metrics like an End Point Error of 12.58 and a Fréchet Inception Distance of 0.42.
To provide a lightweight and cost-effective solution for the long-wave infrared imaging using a singlet, we develop a camera by integrating a High-Frequency-Enhancing Cycle-GAN neural network into a metalens imaging system. The High-Frequency-Enhancing Cycle-GAN improves the quality of the original metalens images by addressing inherent frequency loss introduced by the metalens. In addition to the bidirectional cyclic generative adversarial network, it incorporates a high-frequency adversarial learning module. This module utilizes wavelet transform to extract high-frequency components, and then establishes a high-frequency feedback loop. It enables the generator to enhance the camera outputs by integrating adversarial feedback from the high-frequency discriminator. This ensures that the generator adheres to the constraints imposed by the high-frequency adversarial loss, thereby effectively recovering the camera's frequency loss. This recovery guarantees high-fidelity image output from the camera, facilitating smooth video production. Our camera is capable of achieving dynamic imaging at 125 frames per second with an End Point Error value of 12.58. We also achieve 0.42 for Fréchet Inception Distance, 30.62 for Peak Signal to Noise Ratio, and 0.69 for Structural Similarity in the recorded videos.