推荐 | PULSE:通过对生成模型的潜在空间探索实现自监督照片上采样_推荐一个好地方400字四年级迪士尼游乐园

1.推荐蒲柳人家200字

PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models标题：PULSE:通过对生成模型的潜在空间探索实现自监督照片上采样

2.推荐蒲柳人家

发布时间：2020/07/20 Accepted to CVPR 2020导读 / 我爱计算机视觉：作者提出了一种新的图像超分辨率方法，区别于有监督的PSNR-based和GANs-based方法，该方法是一种无监督的方法，即只需要低分辨率的图片就可以恢复高质量、高分辨率的图片。

3.推荐Pulsec脉冲涡流探伤仪

查看原文导读 / 智东西：马赛克秒变没！杜克大学推AI图像生成器，糊图像5秒变清晰查看原文导读 / 郭一璞 _ 量子位：创造一只AI可能要很复杂的过程，但玩坏一只AI，只要一步就够了杜克大学的PLUSE，这只登上CVPR的最强马赛克修复AI，能让“高糊”画质马赛克人像复原：。

4.推荐一款大屏智能手机

查看原文导读 / AI前线：偏见，人工智能的真正风险当数据存在偏见时，机器学习系统就会存在偏见这个人脸上采样系统让每个人看起来都像白人，因为这个网络是在 FlickFaceHQ 上进行预训练的，其中主要包含白人照片。

5.推荐一本书作文400字

在来自塞内加尔（Senegal，西非国家）的数据集上训练完全相同的系统，每个人看起来都会像非洲人查看原文作者：Sachit Menon, Alexandru Damian, Shijia Hu, Nikhil Ravi, Cynthia Rudin

6.推荐一本好书

链接：https://arxiv.org/abs/2003.03808PDF：https://arxiv.org/pdf/2003.03808.pdf代码：https://github.com.../pulse

7.推荐一个好地方400字四年级

摘要：The primary aim of single-image super-resolution is to construct high-resolution (HR) images from corresponding low-resolution (LR) inputs. In previous approaches, which have generally been supervised, the training objective typically measures a pixel-wise average distance between the super-resolved (SR) and HR images. Optimizing such metrics often leads to blurring, especially in high variance (detailed) regions. We propose an alternative formulation of the super-resolution problem based on creating realistic SR images that downscale correctly. We present an algorithm addressing this problem, PULSE (Photo Upsampling via Latent Space Exploration), which generates high-resolution, realistic images at resolutions previously unseen in the literature. It accomplishes this in an entirely self-supervised fashion and is not confined to a specific degradation operator used during training, unlike previous methods (which require supervised training on databases of LR-HR image pairs). 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, we restrict the search space to guarantee realistic outputs. PULSE thereby generates super-resolved images that both are realistic and downscale correctly. We show proof of concept of our approach in the domain of face super-resolution (i.e., face hallucination). We also present a discussion of the limitations and biases of the method as currently implemented with an accompanying model card with relevant metrics. Our method outperforms state-of-the-art methods in perceptual quality at higher resolutions and scale factors than previously possible.

8.推荐一个好地方

学科：Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Image and Video Processing (eess.IV)