中文
相关论文

相关论文: SHUNIT: Style Harmonization for Unpaired Image-to-…

200 篇论文

Translating information between text and image is a fundamental problem in artificial intelligence that connects natural language processing and computer vision. In the past few years, performance in image caption generation has seen…

计算机视觉与模式识别 · 计算机科学 2017-06-06 Hao Dong , Jingqing Zhang , Douglas McIlwraith , Yike Guo

Image-to-image (I2I) translation has matured in recent years and is able to generate high-quality realistic images. However, despite current success, it still faces important challenges when applied to small domains. Existing methods use…

计算机视觉与模式识别 · 计算机科学 2021-05-17 Yaxing Wang , Hector Laria Mantecon , Joost van de Weijer , Laura Lopez-Fuentes , Bogdan Raducanu

Many image-to-image (I2I) translation problems are in nature of high diversity that a single input may have various counterparts. Prior works proposed the multi-modal network that can build a many-to-many mapping between two visual domains.…

计算机视觉与模式识别 · 计算机科学 2019-10-07 Jialu Huang , Jing Liao , Tak Wu Sam Kwong

Image-to-image translation has recently achieved remarkable results. But despite current success, it suffers from inferior performance when translations between classes require large shape changes. We attribute this to the high-resolution…

计算机视觉与模式识别 · 计算机科学 2020-11-12 Yaxing Wang , Lu Yu , Joost van de Weijer

For a unified analysis of medical images from different modalities, data harmonization using image-to-image (I2I) translation is desired. We study this problem employing an optical coherence tomography (OCT) data set of Spectralis-OCT and…

图像与视频处理 · 电气工程与系统科学 2024-04-09 Marc S. Seibel , Hristina Uzunova , Timo Kepp , Heinz Handels

Recent studies have shown remarkable success in unsupervised image-to-image translation. However, if there has no access to enough images in target classes, learning a mapping from source classes to the target classes always suffers from…

计算机视觉与模式识别 · 计算机科学 2020-07-29 Yuanqi Chen , Xiaoming Yu , Shan Liu , Ge Li

We present a novel unsupervised framework for instance-level image-to-image translation. Although recent advances have been made by incorporating additional object annotations, existing methods often fail to handle images with multiple…

计算机视觉与模式识别 · 计算机科学 2021-04-13 Somi Jeong , Youngjung Kim , Eungbean Lee , Kwanghoon Sohn

We propose a novel method for unsupervised image-to-image translation, which incorporates a new attention module and a new learnable normalization function in an end-to-end manner. The attention module guides our model to focus on more…

计算机视觉与模式识别 · 计算机科学 2020-04-09 Junho Kim , Minjae Kim , Hyeonwoo Kang , Kwanghee Lee

Image-to-image (I2I) translation is a challenging topic in computer vision. We divide this problem into three tasks: strongly constrained translation, normally constrained translation, and weakly constrained translation. The constraint here…

计算机视觉与模式识别 · 计算机科学 2022-07-06 Weichen Fan , Jinghuan Chen , Jiabin Ma , Jun Hou , Shuai Yi

We propose a novel spatially-correlative loss that is simple, efficient and yet effective for preserving scene structure consistency while supporting large appearance changes during unpaired image-to-image (I2I) translation. Previous…

计算机视觉与模式识别 · 计算机科学 2021-04-05 Chuanxia Zheng , Tat-Jen Cham , Jianfei Cai

Given an input image from a source domain and a guidance image from a target domain, unsupervised many-to-many image-to-image (UMMI2I) translation methods seek to generate a plausible example from the target domain that preserves…

计算机视觉与模式识别 · 计算机科学 2021-08-23 Dina Bashkirova , Ben Usman , Kate Saenko

Despite significant advances in image-to-image (I2I) translation with generative adversarial networks (GANs), it remains challenging to effectively translate an image to a set of diverse images in multiple target domains using a single pair…

计算机视觉与模式识别 · 计算机科学 2022-06-30 Shihua Huang , Cheng He , Ran Cheng

Unsupervised image-to-image translation aims to learn the mapping between two visual domains with unpaired samples. Existing works focus on disentangling domain-invariant content code and domain-specific style code individually for…

计算机视觉与模式识别 · 计算机科学 2021-10-28 Yunfei Liu , Haofei Wang , Yang Yue , Feng Lu

Unsupervised image-to-image translation aims at learning the mapping from the source to target domain without using paired images for training. An essential yet restrictive assumption for unsupervised image translation is that the two…

计算机视觉与模式识别 · 计算机科学 2021-09-27 Shaoan Xie , Mingming Gong , Yanwu Xu , Kun Zhang

We introduce a simple and versatile framework for image-to-image translation. We unearth the importance of normalization layers, and provide a carefully designed two-stream generative model with newly proposed feature transformations in a…

计算机视觉与模式识别 · 计算机科学 2020-07-28 Liming Jiang , Changxu Zhang , Mingyang Huang , Chunxiao Liu , Jianping Shi , Chen Change Loy

In this paper, we tackle the challenging task of Panoramic Image-to-Image translation (Pano-I2I) for the first time. This task is difficult due to the geometric distortion of panoramic images and the lack of a panoramic image dataset with…

计算机视觉与模式识别 · 计算机科学 2023-04-12 Soohyun Kim , Junho Kim , Taekyung Kim , Hwan Heo , Seungryong Kim , Jiyoung Lee , Jin-Hwa Kim

Unsupervised image translation aims to learn the transformation from a source domain to another target domain given unpaired training data. Several state-of-the-art works have yielded impressive results in the GANs-based unsupervised…

计算机视觉与模式识别 · 计算机科学 2020-04-21 Taewon Kang , Kwang Hee Lee

Unsupervised image-to-image (I2I) translation learns cross-domain image mapping that transfers input from the source domain to output in the target domain while preserving its semantics. One challenge is that different semantic statistics…

计算机视觉与模式识别 · 计算机科学 2023-10-10 Ganning Zhao , Wenhui Cui , Suya You , C. -C. Jay Kuo

Sketch-to-image (S2I) translation plays an important role in image synthesis and manipulation tasks, such as photo editing and colorization. Some specific S2I translation including sketch-to-photo and sketch-to-painting can be used as…

计算机视觉与模式识别 · 计算机科学 2020-06-19 Jialu Huang , Jing Liao , Zhifeng Tan , Sam Kwong

Image-to-image (I2I) translation is a pixel-level mapping that requires a large number of paired training data and often suffers from the problems of high diversity and strong category bias in image scenes. In order to tackle these…

计算机视觉与模式识别 · 计算机科学 2019-04-22 Liqian Ma , Qianru Sun , Bernt Schiele , Luc Van Gool