English
Related papers

Related papers: Unifying conditional and unconditional semantic im…

200 papers

This work explores conditional image generation with a new image density model based on the PixelCNN architecture. The model can be conditioned on any vector, including descriptive labels or tags, or latent embeddings created by other…

Computer Vision and Pattern Recognition · Computer Science 2016-06-21 Aaron van den Oord , Nal Kalchbrenner , Oriol Vinyals , Lasse Espeholt , Alex Graves , Koray Kavukcuoglu

Conditional generative adversarial networks (cGAN) have led to large improvements in the task of conditional image generation, which lies at the heart of computer vision. The major focus so far has been on performance improvement, while…

Machine Learning · Computer Science 2019-03-14 Grigorios G. Chrysos , Jean Kossaifi , Stefanos Zafeiriou

Understanding the mechanism of generative adversarial networks (GANs) helps us better use GANs for downstream applications. Existing efforts mainly target interpreting unconditional models, leaving it less explored how a conditional GAN…

Computer Vision and Pattern Recognition · Computer Science 2022-03-22 Yingqing He , Zhiyi Zhang , Jiapeng Zhu , Yujun Shen , Qifeng Chen

Joint synthesis of images and segmentation masks with generative adversarial networks (GANs) is promising to reduce the effort needed for collecting image data with pixel-wise annotations. However, to learn high-fidelity image-mask…

Computer Vision and Pattern Recognition · Computer Science 2022-09-19 Vadim Sushko , Dan Zhang , Juergen Gall , Anna Khoreva

In this paper we study image captioning as a conditional GAN training, proposing both a context-aware LSTM captioner and co-attentive discriminator, which enforces semantic alignment between images and captions. We empirically focus on the…

Machine Learning · Computer Science 2019-06-10 Pierre L. Dognin , Igor Melnyk , Youssef Mroueh , Jarret Ross , Tom Sercu

Automatic image synthesis research has been rapidly growing with deep networks getting more and more expressive. In the last couple of years, we have observed images of digits, indoor scenes, birds, chairs, etc. being automatically…

Computer Vision and Pattern Recognition · Computer Science 2016-12-02 Levent Karacan , Zeynep Akata , Aykut Erdem , Erkut Erdem

This paper investigates a novel problem of generating images from visual attributes. We model the image as a composite of foreground and background and develop a layered generative model with disentangled latent variables that can be…

Machine Learning · Computer Science 2016-10-11 Xinchen Yan , Jimei Yang , Kihyuk Sohn , Honglak Lee

We propose a novel ECGAN for the challenging semantic image synthesis task. Although considerable improvements have been achieved by the community in the recent period, the quality of synthesized images is far from satisfactory due to three…

Computer Vision and Pattern Recognition · Computer Science 2023-07-25 Hao Tang , Guolei Sun , Nicu Sebe , Luc Van Gool

Text-to-image synthesis (T2I) aims to generate photo-realistic images which are semantically consistent with the text descriptions. Existing methods are usually built upon conditional generative adversarial networks (GANs) and initialize an…

Computer Vision and Pattern Recognition · Computer Science 2022-03-25 Kai Hu , Wentong Liao , Michael Ying Yang , Bodo Rosenhahn

Among the major remaining challenges for generative adversarial networks (GANs) is the capacity to synthesize globally and locally coherent images with object shapes and textures indistinguishable from real images. To target this issue we…

Computer Vision and Pattern Recognition · Computer Science 2021-03-23 Edgar Schönfeld , Bernt Schiele , Anna Khoreva

This paper introduces a novel and fully unsupervised framework for conditional GAN training in which labels are automatically obtained from data. We incorporate a clustering network into the standard conditional GAN framework that plays…

Computer Vision and Pattern Recognition · Computer Science 2020-12-04 Mehdi Noroozi

Exploiting learning algorithms under scarce data regimes is a limitation and a reality of the medical imaging field. In an attempt to mitigate the problem, we propose a data augmentation protocol based on generative adversarial networks. We…

Image and Video Processing · Electrical Eng. & Systems 2021-03-30 Ahmad B Qasim , Ivan Ezhov , Suprosanna Shit , Oliver Schoppe , Johannes C Paetzold , Anjany Sekuboyina , Florian Kofler , Jana Lipkova , Hongwei Li , Bjoern Menze

Generative adversarial network (GAN) has greatly improved the quality of unsupervised image generation. Previous GAN-based methods often require a large amount of high-quality training data while producing a small number (e.g., tens) of…

Computer Vision and Pattern Recognition · Computer Science 2019-09-26 Chunpeng Wu , Wei Wen , Yiran Chen , Hai Li

In this paper we investigate image generation guided by hand sketch. When the input sketch is badly drawn, the output of common image-to-image translation follows the input edges due to the hard condition imposed by the translation process.…

Computer Vision and Pattern Recognition · Computer Science 2018-07-27 Yongyi Lu , Shangzhe Wu , Yu-Wing Tai , Chi-Keung Tang

We develop a novel method for training of GANs for unsupervised and class conditional generation of images, called Linear Discriminant GAN (LD-GAN). The discriminator of an LD-GAN is trained to maximize the linear separability between…

Machine Learning · Statistics 2017-07-26 Zhun Sun , Mete Ozay , Takayuki Okatani

In recent years, considerable advancements have been made in the area of Generative Adversarial Networks (GANs), particularly with the advent of style-based architectures that address many key shortcomings - both in terms of modeling…

Computer Vision and Pattern Recognition · Computer Science 2022-08-04 Nikos Kostagiolas , Mihalis A. Nicolaou , Yannis Panagakis

Automatic analysis of spatio-temporal microscopy images is inevitable for state-of-the-art research in the life sciences. Recent developments in deep learning provide powerful tools for automatic analyses of such image data, but heavily…

Image and Video Processing · Electrical Eng. & Systems 2021-01-28 Dennis Bähr , Dennis Eschweiler , Anuk Bhattacharyya , Daniel Moreno-Andrés , Wolfram Antonin , Johannes Stegmaier

Training effective Generative Adversarial Networks (GANs) requires large amounts of training data, without which the trained models are usually sub-optimal with discriminator over-fitting. Several prior studies address this issue by…

Computer Vision and Pattern Recognition · Computer Science 2021-12-07 Kaiwen Cui , Jiaxing Huang , Zhipeng Luo , Gongjie Zhang , Fangneng Zhan , Shijian Lu

This dissertation attempts to drive innovation in the field of generative modeling for computer vision, by exploring novel formulations of conditional generative models, and innovative applications in images, 3D animations, and video. Our…

Computer Vision and Pattern Recognition · Computer Science 2023-10-23 Vikram Voleti

Image-to-image translation tasks have been widely investigated with Generative Adversarial Networks (GANs) and dual learning. However, existing models lack the ability to control the translated results in the target domain and their results…

Computer Vision and Pattern Recognition · Computer Science 2018-05-02 Jianxin Lin , Yingce Xia , Tao Qin , Zhibo Chen , Tie-Yan Liu