Emerging Disentanglement in Auto-Encoder Based Unsupervised Image Content Transfer

Press, Ori; Galanti, Tomer; Benaim, Sagie; Wolf, Lior

doi:10.48550/arxiv.2001.05017

Cited by 8 publications

(8 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the field of image generation, many designs with adversarial theory as the base have produced unforgettable impression. CycleGAN [46] utilized cycle consistency principle to enhance GAN for unsupervised image style transfer, which also was extended to some other image generation methods and achieved amazing results [39,40,7]. Motivated by the high quality of StyleGAN [22,23], which performs exceptionally well on image editing and processing tasks.…”

Section: Related Workmentioning

confidence: 99%

Underwater Light Field Retention : Neural Rendering for Underwater Imaging

Tian¹,

Chen²,

Liu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Underwater Image Rendering aims to generate a true-tolife underwater image from a given clean one, which could be applied to various practical applications such as underwater image enhancement, camera filter, and virtual gaming. We explore two less-touched but challenging problems in underwater image rendering, namely, i) how to render diverse underwater scenes by a single neural network? ii) how to adaptively learn the underwater light fields from natural exemplars, i,e., realistic underwater images? To this end, we propose a neural rendering method for underwater imaging, dubbed UWNR (Underwater Neural Rendering). Specifically, UWNR is a data-driven neural network that implicitly learns the natural degenerated model from authentic underwater images, avoiding introducing erroneous biases by hand-craft imaging models.Compared with existing underwater image generation methods, UWNR utilizes the natural light field to simulate the main characteristics of the underwater scene. Thus, it is able to synthesize a wide variety of underwater images from one clean image with various realistic underwater images.Extensive experiments demonstrate that our approach achieves better visual effects and quantitative metrics over previous methods. Moreover, we adopt UWNR to build an open Large Neural Rendering Underwater Dataset containing various types of water quality, dubbed LNRUD.

show abstract

Section: Related Workmentioning

confidence: 99%

Underwater Light Field Retention : Neural Rendering for Underwater Imaging

Tian¹,

Chen²,

Liu³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Semantic manipulation tries to edit the high-level semantics of an image, such as the presence and appearance of objects (image composition) [186] with or without makeup [187]. Attribute manipulation [159], [170], [167] varies the binary representations to edit image attributes, such as the gender of the subject [224], the color of hair [145], [174] and the presence of glasses [225], and perform image relabeling [186]. Moreover, image/video retargeting [188] enables the transfer of sequential content from one domain to another while preserving the style of the target domain.…”

Section: Applicationmentioning

confidence: 99%

Image-to-Image Translation: Methods and Applications

Pang¹,

Lin²,

Qin³

et al. 2021

Preprint

View full text Add to dashboard Cite

Image-to-image translation (I2I) aims to transfer images from a source domain to a target domain while preserving the content representations. I2I has drawn increasing attention and made tremendous progress in recent years because of its wide range of applications in many computer vision and image processing problems, such as image synthesis, segmentation, style transfer, restoration, and pose estimation. In this paper, we provide an overview of the I2I works developed in recent years.We will analyze the key techniques of the existing I2I works and clarify the main progress the community has made. Additionally, we will elaborate on the effect of I2I on the research and industry community and point out remaining challenges in related fields.Index Terms-image-to-image translation, two-domain I2I, multi-domain I2I, supervised methods, unsupersived methods, semi-supervised methods, few-shot methods Yingxue Pang, Jianxin Lin, and Zhibo Chen are with the De-

show abstract

“…Sentence-based image editing. In recent years, based on Generative Adversarial Networks (GANs) [17,30,33,39,46,48], researchers pay much attention to the image generation or transformation from text or image, such as Text-to-Image Generation [26,31,37,42,43] and Image-to-Image Translation [12,29,38,40]. To make the transformation controllable, Text-based Image Editing will only edit the target area of the image through text description.…”

Section: Related Workmentioning

confidence: 99%

Each Attribute Matters: Contrastive Attention for Sentence-based Image Editing

Zhao¹,

Lyu²,

Hu³

et al. 2021

Preprint

View full text Add to dashboard Cite

Sentence-based Image Editing (SIE) aims to deploy natural language to edit an image. Offering potentials to reduce expensive manual editing, SIE has attracted much interest recently. However, existing methods can hardly produce accurate editing and even lead to failures in attribute editing when the query sentence is with multiple editable attributes. To cope with this problem, by focusing on enhancing the difference between attributes, this paper proposes a novel model called Contrastive Attention Generative Adversarial Network (CA-GAN), which is inspired from contrastive training. Specifically, we first design a novel contrastive attention module to enlarge the editing difference between random combinations of attributes which are formed during training. We then construct an attribute discriminator to ensure effective editing on each attribute. A series of experiments show that our method can generate very encouraging results in sentencebased image editing with multiple attributes on CUB and COCO dataset. Our code is available at https://github.com/Zlq2021/CA-GAN IntroductionAs billions of images are uploaded and shared every day [16,32], image editing has become one of the most demanding tasks in social media. However, to edit an image as desired, one may have to master professional software such as Adobe PhotoShop. In contrast with manual editing, automatic image editing, has recently attracted much interest in computer vision. This paper studies the problem of Sentence-based Image Editing (SIE) [7,19,25] that intends to deploy natural language to assist image editing automatically. One main

show abstract

Emerging Disentanglement in Auto-Encoder Based Unsupervised Image Content Transfer

Cited by 8 publications

References 17 publications

Underwater Light Field Retention : Neural Rendering for Underwater Imaging

Underwater Light Field Retention : Neural Rendering for Underwater Imaging

Image-to-Image Translation: Methods and Applications

Each Attribute Matters: Contrastive Attention for Sentence-based Image Editing

Contact Info

Product

Resources

About