中文
相关论文

相关论文: HyperEditor: Achieving Both Authenticity and Cross…

200 篇论文

The introduction of high-quality image generation models, particularly the StyleGAN family, provides a powerful tool to synthesize and manipulate images. However, existing models are built upon high-quality (HQ) data as desired outputs,…

计算机视觉与模式识别 · 计算机科学 2022-12-08 Dat Viet Thanh Nguyen , Phong Tran The , Tan M. Dinh , Cuong Pham , Anh Tuan Tran

Our world is marked by unprecedented technological, global, and socio-political transformations, posing a significant challenge to text-to-image generative models. These models encode factual associations within their parameters that can…

计算与语言 · 计算机科学 2024-05-08 Dana Arad , Hadas Orgad , Yonatan Belinkov

The exploration of the latent space in StyleGANs and GAN inversion exemplify impressive real-world image editing, yet the trade-off between reconstruction quality and editing quality remains an open problem. In this study, we revisit…

计算机视觉与模式识别 · 计算机科学 2023-06-02 Kai Katsumata , Duc Minh Vo , Bei Liu , Hideki Nakayama

Arbitrary attribute editing generally can be tackled by incorporating encoder-decoder and generative adversarial networks. However, the bottleneck layer in encoder-decoder usually gives rise to blurry and low quality editing result. And…

计算机视觉与模式识别 · 计算机科学 2019-04-24 Ming Liu , Yukang Ding , Min Xia , Xiao Liu , Errui Ding , Wangmeng Zuo , Shilei Wen

Existing methods for image synthesis utilized a style encoder based on stacks of convolutions and pooling layers to generate style codes from input images. However, the encoded vectors do not necessarily contain local information of the…

计算机视觉与模式识别 · 计算机科学 2021-12-20 Jonghyun Kim , Gen Li , Cheolkon Jung , Joongkyu Kim

New advancements for the detection of synthetic images are critical for fighting disinformation, as the capabilities of generative AI models continuously evolve and can lead to hyper-realistic synthetic imagery at unprecedented scale and…

计算机视觉与模式识别 · 计算机科学 2023-04-25 Pantelis Dogoulis , Giorgos Kordopatis-Zilos , Ioannis Kompatsiaris , Symeon Papadopoulos

Inspired by the ability of StyleGAN to generate highly realistic images in a variety of domains, much recent work has focused on understanding how to use the latent spaces of StyleGAN to manipulate generated and real images. However,…

计算机视觉与模式识别 · 计算机科学 2021-04-01 Or Patashnik , Zongze Wu , Eli Shechtman , Daniel Cohen-Or , Dani Lischinski

Generative adversarial networks (GANs) have recently found applications in image editing. However, most GAN based image editing methods often require large scale datasets with semantic segmentation annotations for training, only provide…

计算机视觉与模式识别 · 计算机科学 2021-11-08 Huan Ling , Karsten Kreis , Daiqing Li , Seung Wook Kim , Antonio Torralba , Sanja Fidler

Neural networks have proven their capabilities by outperforming many other approaches on regression or classification tasks on various kinds of data. Other astonishing results have been achieved using neural nets as data generators,…

计算机视觉与模式识别 · 计算机科学 2018-10-16 Andrej Junginger , Markus Hanselmann , Thilo Strauss , Sebastian Boblest , Jens Buchner , Holger Ulmer

We propose a novel lightweight generative adversarial network for efficient image manipulation using natural language descriptions. To achieve this, a new word-level discriminator is proposed, which provides the generator with fine-grained…

计算机视觉与模式识别 · 计算机科学 2020-10-26 Bowen Li , Xiaojuan Qi , Philip H. S. Torr , Thomas Lukasiewicz

Recent studies have shown remarkable success in the unsupervised image to image (I2I) translation. However, due to the imbalance in the data, learning joint distribution for various domains is still very challenging. Although existing…

计算机视觉与模式识别 · 计算机科学 2021-06-24 Jihye Back

Our paper addresses the complex task of transferring a hairstyle from a reference image to an input photo for virtual hair try-on. This task is challenging due to the need to adapt to various photo poses, the sensitivity of hairstyles, and…

计算机视觉与模式识别 · 计算机科学 2024-05-28 Maxim Nikolaev , Mikhail Kuznetsov , Dmitry Vetrov , Aibek Alanov

Recent work has shown that a variety of semantics emerge in the latent space of Generative Adversarial Networks (GANs) when being trained to synthesize images. However, it is difficult to use these learned semantics for real image editing.…

计算机视觉与模式识别 · 计算机科学 2020-07-17 Jiapeng Zhu , Yujun Shen , Deli Zhao , Bolei Zhou

We present a generic image-to-image translation framework, pixel2style2pixel (pSp). Our pSp framework is based on a novel encoder network that directly generates a series of style vectors which are fed into a pretrained StyleGAN generator,…

计算机视觉与模式识别 · 计算机科学 2021-04-22 Elad Richardson , Yuval Alaluf , Or Patashnik , Yotam Nitzan , Yaniv Azar , Stav Shapiro , Daniel Cohen-Or

Despite recent advances in semantic manipulation using StyleGAN, semantic editing of real faces remains challenging. The gap between the $W$ space and the $W$+ space demands an undesirable trade-off between reconstruction quality and…

计算机视觉与模式识别 · 计算机科学 2022-07-22 Heyi Li , Jinlong Liu , Xinyu Zhang , Yunzhi Bai , Huayan Wang , Klaus Mueller

Generative models are widely employed to enhance the photorealism of visual synthetic data for training computer vision algorithms. However, they often introduce visual artifacts that degrade the accuracy of these algorithms and require…

计算机视觉与模式识别 · 计算机科学 2026-03-19 Stefanos Pasios , Nikos Nikolaidis

Understating and controlling generative models' latent space is a complex task. In this paper, we propose a novel method for learning to control any desired attribute in a pre-trained GAN's latent space, for the purpose of editing…

计算机视觉与模式识别 · 计算机科学 2021-11-18 Nir Diamant , Nitsan Sandor , Alex M Bronstein

Recent inversion methods have shown that real images can be inverted into StyleGAN's latent space and numerous edits can be achieved on those images thanks to the semantically rich feature representations of well-trained GAN models.…

计算机视觉与模式识别 · 计算机科学 2023-07-28 Ahmet Burak Yildirim , Hamza Pehlivan , Bahri Batuhan Bilecen , Aysegul Dundar

The exploration of the latent space in StyleGANs and GAN inversion exemplify impressive real-world image editing, yet the trade-off between reconstruction quality and editing quality remains an open problem. In this study, we revisit…

计算机视觉与模式识别 · 计算机科学 2023-07-19 Kai Katsumata , Duc Minh Vo , Bei Liu , Hideki Nakayama

Portrait stylization is a long-standing task enabling extensive applications. Although 2D-based methods have made great progress in recent years, real-world applications such as metaverse and games often demand 3D content. On the other…

计算机视觉与模式识别 · 计算机科学 2023-04-20 Zhuo Chen , Xudong Xu , Yichao Yan , Ye Pan , Wenhan Zhu , Wayne Wu , Bo Dai , Xiaokang Yang