论文标题
迈向微小的感知超级分辨率的旅程
Journey Towards Tiny Perceptual Super-Resolution
论文作者
论文摘要
单图像感知超分辨率（SR）的最新作品在通过深度卷积网络生成逼真的纹理方面表现出了前所未有的性能。但是，这些卷积模型过于大且昂贵，阻碍了它们有效部署到结束设备。在这项工作中，我们提出了一种神经体系结构搜索（NAS）方法，该方法将NAS和生成的对抗网络（GAN）与最新的感知SR的进步相结合，并推动了小型感知SR模型的效率以促进设备执行。具体而言，我们依次搜索生成器和鉴别器的体系结构，突出了搜索SR优化歧视器的独特挑战和关键观察，并将其与文献中现有的歧视器结构进行了比较。我们的微小感知SR（TPSR）模型在全参考感知度量（LPIPS）和失真度量（PSNR）上的表现优于SRGAN和ENHANCENET，同时分别高达26.4 $ \ times $ \ times Memory Emality和33.6 $ 33.6 $ \ times $ $ \ times $更高的计算高效。
Recent works in single-image perceptual super-resolution (SR) have demonstrated unprecedented performance in generating realistic textures by means of deep convolutional networks. However, these convolutional models are excessively large and expensive, hindering their effective deployment to end devices. In this work, we propose a neural architecture search (NAS) approach that integrates NAS and generative adversarial networks (GANs) with recent advances in perceptual SR and pushes the efficiency of small perceptual SR models to facilitate on-device execution. Specifically, we search over the architectures of both the generator and the discriminator sequentially, highlighting the unique challenges and key observations of searching for an SR-optimized discriminator and comparing them with existing discriminator architectures in the literature. Our tiny perceptual SR (TPSR) models outperform SRGAN and EnhanceNet on both full-reference perceptual metric (LPIPS) and distortion metric (PSNR) while being up to 26.4$\times$ more memory efficient and 33.6$\times$ more compute efficient respectively.
