中文
相关论文

相关论文: Generative Fields: Uncovering Hierarchical Feature…

200 篇论文

Current generative frameworks use end-to-end learning and generate images by sampling from uniform noise distribution. However, these approaches ignore the most basic principle of image formation: images are product of: (a) Structure: the…

计算机视觉与模式识别 · 计算机科学 2016-07-27 Xiaolong Wang , Abhinav Gupta

Generative Adversarial Networks (GAN) is currently widely used as an unsupervised image generation method. Current state-of-the-art GANs can generate photorealistic images with high resolution. However, a large amount of data is required,…

计算机视觉与模式识别 · 计算机科学 2022-11-16 Pengwei Wang

GAN inversion and editing via StyleGAN maps an input image into the embedding spaces ($\mathcal{W}$, $\mathcal{W^+}$, and $\mathcal{F}$) to simultaneously maintain image fidelity and meaningful manipulation. From latent space $\mathcal{W}$…

计算机视觉与模式识别 · 计算机科学 2023-03-28 Hongyu Liu , Yibing Song , Qifeng Chen

Recent advances in high-fidelity semantic image editing heavily rely on the presumably disentangled latent spaces of the state-of-the-art generative models, such as StyleGAN. Specifically, recent works show that it is possible to achieve…

计算机视觉与模式识别 · 计算机科学 2021-11-30 Valentin Khrulkov , Leyla Mirvakhabova , Ivan Oseledets , Artem Babenko

Recent advances in the field of generative models and in particular generative adversarial networks (GANs) have lead to substantial progress for controlled image editing, especially compared with the pre-deep learning era. Despite their…

计算机视觉与模式识别 · 计算机科学 2023-12-14 Gwilherm Lesné , Yann Gousseau , Saïd Ladjal , Alasdair Newson

This paper proposes an extension to the Generative Adversarial Networks (GANs), namely as ARTGAN to synthetically generate more challenging and complex images such as artwork that have abstract characteristics. This is in contrast to most…

计算机视觉与模式识别 · 计算机科学 2017-04-20 Wei Ren Tan , Chee Seng Chan , Hernan Aguirre , Kiyoshi Tanaka

The high-quality images yielded by generative adversarial networks (GANs) have motivated investigations into their application for image editing. However, GANs are often limited in the control they provide for performing specific edits. One…

计算机视觉与模式识别 · 计算机科学 2022-11-23 Krishnakant Singh , Simone Schaub-Meyer , Stefan Roth

Making generative models 3D-aware bridges the 2D image space and the 3D physical world yet remains challenging. Recent attempts equip a Generative Adversarial Network (GAN) with a Neural Radiance Field (NeRF), which maps 3D coordinates to…

计算机视觉与模式识别 · 计算机科学 2022-04-19 Yinghao Xu , Sida Peng , Ceyuan Yang , Yujun Shen , Bolei Zhou

Text-to-image diffusion models have remarkably excelled in producing diverse, high-quality, and photo-realistic images. This advancement has spurred a growing interest in incorporating specific identities into generated content. Most…

计算机视觉与模式识别 · 计算机科学 2023-11-30 Xiaoming Li , Xinyu Hou , Chen Change Loy

Photo-realistic re-rendering of a human from a single image with explicit control over body pose, shape and appearance enables a wide range of applications, such as human appearance transfer, virtual try-on, motion imitation, and novel view…

计算机视觉与模式识别 · 计算机科学 2021-02-23 Kripasindhu Sarkar , Vladislav Golyanik , Lingjie Liu , Christian Theobalt

One of the main motivations for training high quality image generative models is their potential use as tools for image manipulation. Recently, generative adversarial networks (GANs) have been able to generate images of remarkable quality.…

计算机视觉与模式识别 · 计算机科学 2019-07-01 Aviv Gabbay , Yedid Hoshen

Recent advances in face manipulation using StyleGAN have produced impressive results. However, StyleGAN is inherently limited to cropped aligned faces at a fixed image resolution it is pre-trained on. In this paper, we propose a simple and…

计算机视觉与模式识别 · 计算机科学 2023-07-24 Shuai Yang , Liming Jiang , Ziwei Liu , Chen Change Loy

Latent space exploration is a technique that discovers interpretable latent directions and manipulates latent codes to edit various attributes in images generated by generative adversarial networks (GANs). However, in previous work, spatial…

计算机视觉与模式识别 · 计算机科学 2022-08-29 Yuki Endo

We present a new perspective of achieving image synthesis by viewing this task as a visual token generation problem. Different from existing paradigms that directly synthesize a full image from a single input (e.g., a latent code), the new…

计算机视觉与模式识别 · 计算机科学 2021-12-21 Yanhong Zeng , Huan Yang , Hongyang Chao , Jianbo Wang , Jianlong Fu

Synthetically generated images can be used to create media content or to complement datasets for training image analysis models. Several methods have recently been proposed for the synthesis of high-fidelity face images; however, the…

机器学习 · 计算机科学 2024-05-21 Emmanouil Maragkoudakis , Symeon Papadopoulos , Iraklis Varlamis , Christos Diou

Recent advances in generative adversarial networks (GANs) have led to remarkable achievements in face image synthesis. While methods that use style-based GANs can generate strikingly photorealistic face images, it is often difficult to…

计算机视觉与模式识别 · 计算机科学 2021-11-02 Safa C. Medin , Bernhard Egger , Anoop Cherian , Ye Wang , Joshua B. Tenenbaum , Xiaoming Liu , Tim K. Marks

High quality facial image editing is a challenging problem in the movie post-production industry, requiring a high degree of control and identity preservation. Previous works that attempt to tackle this problem may suffer from the…

计算机视觉与模式识别 · 计算机科学 2021-08-18 Xu Yao , Alasdair Newson , Yann Gousseau , Pierre Hellier

Existing GAN inversion methods fail to provide latent codes for reliable reconstruction and flexible editing simultaneously. This paper presents a transformer-based image inversion and editing model for pretrained StyleGAN which is not only…

计算机视觉与模式识别 · 计算机科学 2022-03-16 Xueqi Hu , Qiusheng Huang , Zhengyi Shi , Siyuan Li , Changxin Gao , Li Sun , Qingli Li

GANs can generate photo-realistic images from the domain of their training data. However, those wanting to use them for creative purposes often want to generate imagery from a truly novel domain, a task which GANs are inherently unable to…

计算机视觉与模式识别 · 计算机科学 2020-11-24 Justin N. M. Pinkney , Doron Adler

3D-controllable portrait synthesis has significantly advanced, thanks to breakthroughs in generative adversarial networks (GANs). However, it is still challenging to manipulate existing face images with precise 3D control. While…

计算机视觉与模式识别 · 计算机科学 2022-08-25 Yuchen Liu , Zhixin Shu , Yijun Li , Zhe Lin , Richard Zhang , S. Y. Kung