[2011.04181] Two-Stream Appearance Transfer Network for Person Image Generationopen searchopen navigation menucontact arXivsubscribe to arXiv mailings

Pose guided person image generation means to generate a photo-realistic person image conditioned on an input person image and a desired pose. This task requires spatial manipulation of the source image according to the target pose. However, the generative adversarial networks (GANs) widely used for image generation and translation rely on spatially local and translation equivariant operators, i.e., convolution, pooling and unpooling, which cannot handle large image deformation. This paper introduces a novel two-stream appearance transfer network (2s-ATN) to address this challenge. It is a multi-stage architecture consisting of a source stream and a target stream. Each stage features an appearance transfer module and several two-stream feature fusion modules. The former finds the dense correspondence between the two-stream feature maps and then transfers the appearance information from the source stream to the target stream. The latter exchange local information between the two streams

3 mentions: @AkiraTOSEI@ak92501@AkiraTOSEI
Date: 2020/11/18 11:22

Referring Tweets

@AkiraTOSEI t.co/2rbrZzKzfq The pose transfer GAN; it is structured to be processed in two stream networks, integrating the source and target with an AT module using Query, Key, and Value, like a Transformer. t.co/CkYP8YLtdR
@AkiraTOSEI t.co/2rbrZzKzfq 体勢の転移を行うGAN。TransformerのようなQuery, Key, Valueを使ったATモジュールで転移元と転移先の統合を行いながら2つのネットワークで処理する構造となっている。 t.co/a0srkUnNzK

Related Entries

Read more [2002.04724] Improved Consistency Regularization for GANscontact arXivarXiv Twitter
0 users, 7 mentions 2020/02/13 20:21
Read more [2008.00951] Encoding in Style: a StyleGAN Encoder for Image-to-Image Translationopen searchopen nav...
0 users, 3 mentions 2020/08/11 14:21
Read more [2009.13829] TinyGAN: Distilling BigGAN for Conditional Image Generationopen searchopen navigation m...
0 users, 4 mentions 2020/10/07 11:21
Read more [2010.11422] Learning Loss for Test-Time Augmentationopen searchopen navigation menucontact arXivsub...
0 users, 6 mentions 2020/10/23 08:22
Read more [2010.14701] Scaling Laws for Autoregressive Generative Modelingopen searchopen navigation menuconta...
0 users, 8 mentions 2020/10/29 02:21