MPRNet

2000년 도입 · 논문 3편에서 사용

MPRNet is a multi-stage progressive image restoration architecture that progressively learns restoration functions for the degraded inputs, thereby breaking down the overall recovery process into more manageable steps. Specifically, the model first learns the contextualized features using encoder-decoder architectures and later combines them with a high-resolution branch that retains local information. At each stage, a per-pixel adaptive design is introduced that leverages in-situ supervised attention to reweight the local features.

출처: Multi-Stage Progressive Image Restoration

소개 논문: Multi-Stage Progressive Image Restoration