weixin_44576861的博客

Abstract Most image completion methods produce only one result for each masked input, although there may be many reasonable possibilities. In this paper, we present an approach for pluralistic image completion – the task of generating multiple and diverse plausible solutions for image completion. A major challenge faced by learning-based approaches is that usually only one ground truth training instance per label. As such, sampling from conditional VAEs still leads to minimal diversity. To overcome this, we propose a novel and probabilistically principled framework with two parallel paths. One is a reconstructive path that utilizes the only one given ground truth to get prior distribution of missing parts and rebuild the original image from this distribution. The other is a generative path for which the conditional prior is coupled to the distribution obtained in the reconstructive path. Both are supported by GANs. We also introduce a new short+long term attention layer that exploits distant relations among decoder and encoder features, improving appearance consistency. When tested on datasets with buildings (Paris), faces (CelebA-HQ), and natural images (ImageNet), our method not only generated higherquality completion results, but also with multiple and diverse plausible outputs.

Abstract Super resolution (SR) methods typically assume that the low-resolution (LR) image was downscaled from the unknown high-resolution (HR) image by a fixed ‘ideal’ downscaling kernel (e.g. Bicubic downscaling). However, this is rarely the case in real LR images, in contrast to synthetically generated SR datasets. When the assumed downscaling kernel deviates from the true one, the performance of SR methods significantly deteriorates. This gave rise to Blind-SR – namely, SR when the downscaling kernel (“SR-kernel”) is unknown. It was further shown that the true SR-kernel is the one that maximizes the recurrence of patches across scales of the LR image. In this paper we show how this powerful cross-scale recurrence property can be realized using Deep Internal Learning. We introduce “KernelGAN”, an image-specific Internal-GAN [29], which trains solely on the LR test image at test time, and learns its internal distribution of patches. Its Generator is trained to produce a downscaled version of the LR test image, such that its Discriminator cannot distinguish between the patch distribution of the downscaled image, and the patch distribution of the original LR image. The Generator, once trained, constitutes the downscaling operation with the correct image-specific SR-kernel. KernelGAN is fully unsupervised, requires no training data other than the input image itself, and leads to state-of-the-art results in Blind-SR when plugged into existing SR algorithms. 1

Abstract The style-based GAN architecture (StyleGAN) yields state-of-the-art results in data-driven unconditional generative image modeling. We expose and analyze several of its characteristic artifacts, and propose changes in both model architecture and training methods to address them. In particular, we redesign generator normalization, revisit progressive growing, and regularize the generator to encourage good conditioning in the mapping from latent vectors to images. In addition to improving image quality, this path length regularizer yields the additional benefit that the generator becomes significantly easier to invert. This makes it possible to reliably detect if an image is generated by a particular network. We furthermore visualize how well the generator utilizes its output resolution, and identify a capacity problem, motivating us to train larger models for additional quality improvements. Overall, our improved model rede- fines the state of the art in unconditional image modeling, both in terms of existing distribution quality metrics as well as perceived image quality.

以采访的形式展现了一个斯坦福教授John McCarthy对未来人工智能的各种看法，如今看来可以被称为预言

This book grew out of courses in pricing and revenue optimization developed at Columbia University and Stanford University. 1 At the time there were few other comparable courses. 2 Since then, it has become clear that there is growing interest in pricing and revenue opti- mization (a.k.a. revenue management and dynamic pricing) as a topic of study within both business schools and management science/operations research departments. This interest is quite understandable: Not only is pricing and revenue optimization an important appli- cations arena for quantitative analysis, it has achieved widely publicized successes in many industries, and there is growing interest in the techniques of pricing and revenue optimiza- tion across many different industries. Some of the issues involved in developing and teach- ing an MBA course in pricing and revenue optimization have been treated in articles by Peter Bell (2004) and myself (Phillips 2004).