ENAF：用于大图像超分辨率的自适应补丁融合多出口网络
ENAF: A Multi-Exit Network with an Adaptive Patch Fusion for Large Image Super Resolution
- Hanoi University of Science and Technology（河内理工大学）
- Seoul National University（首尔大学）
机构由 AI 辅助整理，请以论文原文为准。
中文总结 AI 辅助
ENAF是带自适应补丁融合的SISR动态网络，通过嵌入小型PSNR估计网络优化补丁分配，在常用数据集上结合主流骨干网络可提升SISR的质量-复杂度权衡效果
中文摘要 AI 辅助
为了加速单图像超分辨率（SISR）网络在2K-8K大图像上的运行，近期诸多方法将图像分解为小补丁，并根据补丁难度动态确定执行路径（此类网络称为动态网络）。为量化补丁难度，这些方法主要依赖手工设计的评估分数（如边缘），但该分数仅弱关联补丁纹理与SISR模型的计算复杂度。为解决该问题，本文提出ENAF——一种带自适应补丁融合的SISR动态网络。ENAF以骨干网络为基础，整合多个早期出口（EEs）以应对SISR模型参数过多的问题；更重要的是，ENAF嵌入了一个小型网络，用于估计PSNR，以建立EE处数据纹理与计算成本的关联。基于该分数，ENAF可有效将图像补丁分配至对应出口，优化质量-复杂度的权衡。在常用数据集上结合主流SISR骨干网络开展的大量实验，验证了ENAF在各类设置下的有效性。源代码可在该https URL获取。
英文摘要
To accelerate single image super-resolution (SISR) networks on large images (2K-8K), many recent approaches decompose an image into small patches and dynamically determine an execution path according to its difficulty (referred to as a dynamic network). To quantify the hardness of a patch, they mainly rely on a handcrafted assessment score, e.g., edge, which weakly associates a patch's texture with the computational complexity of a SISR model. To address the problem, we introduce ENAF - a dynamic network for SISR with an adaptive patch fusion. Built on top of a backbone, ENAF incorporates multiple early exits (EEs) to tackle the over-parameterized SISR model. More importantly, ENAF plugs a tiny network that estimates PSNR to associate data texture with a computation cost at an EE. Based on the scores, ENAF effectively assigns image patches to an exit, enhancing the quality-complexity trade-off. Extensive experiments on common datasets with popular SISR backbones demonstrate the effectiveness of ENAF in various settings. The source code is provided in https://github.com/nmduonggg/ENAF
