[1612.03242] StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks

Synthesizing high-quality images from text descriptions is a challenging problem in computer vision and has many practical applications. Samples generated by existing text-to-image approaches can roughly reflect the meaning of the given descriptions, but they fail to contain necessary details and vivid object parts. In this paper, we propose Stacked Generative Adversarial Networks (StackGAN) to generate 256x256 photo-realistic images conditioned on text descriptions. We decompose the hard problem into more manageable sub-problems through a sketch-refinement process. The Stage-I GAN sketches the primitive shape and colors of the object based on the given text description, yielding Stage-I low-resolution images. The Stage-II GAN takes Stage-I results and text descriptions as inputs, and generates high-resolution images with photo-realistic details. It is able to rectify defects in Stage-I results and add compelling details with the refinement process. To improve the diversity of the synt

1 mentions: @shion_honda
Date: 2019/04/23 12:47

Referring Tweets

@shion_honda StackGAN [Zhang+, 2017, ICCV] 説明文から256*256pxの対応画像を生成するStackGANを提案。2段構成で、1段目では粗い画像を生成し、2段目では画像の精細化を担う。データ拡張手法として、説明文の埋め込みに摂動を加えるConditioning Augmentationも提案。 t.co/iz5khvxagH #NowReading t.co/m69u8yaX5E

Bookmark Comments

Related Entries

Read more [1805.09501] AutoAugment: Learning Augmentation Policies from Data
7 users, 1 mentions 2019/06/27 05:16
Read more [1908.05257] Few-Shot Learning with Global Class Representations
2 users, 0 mentions 2019/08/15 06:48
Read more [1908.05217] Detecting 11K Classes: Large Scale Object Detection without Fine-Grained Bounding Boxes
2 users, 0 mentions 2019/08/15 06:48
Read more [1908.05858] daBNN: A Super Fast Inference Framework for Binary Neural Networks on ARM devices
2 users, 0 mentions 2019/08/19 09:46
Read more [1802.01548] Regularized Evolution for Image Classifier Architecture Searchcontact arXivarXiv Twitte...
3 users, 2 mentions 2020/04/14 12:58