PULSE

2000년 도입 · 논문 5편에서 사용

PULSE is a self-supervised photo upsampling algorithm. Instead of starting with the LR image and slowly adding detail, PULSE traverses the high-resolution natural image manifold, searching for images that downscale to the original LR image. This is formalized through the downscaling loss, which guides exploration through the latent space of a generative model. By leveraging properties of high-dimensional Gaussians, the authors aim to restrict the search space to guarantee realistic outputs.

출처: PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models

소개 논문: PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models