scholarly journals PCGAN: Partition-Controlled Human Image Generation

2019 ◽  
Vol 33 ◽  
pp. 8698-8705 ◽  
Author(s):  
Dong Liang ◽  
Rui Wang ◽  
Xiaowei Tian ◽  
Cong Zou
Keyword(s):  
Image Generation ◽  
Human Pose ◽  
Human Image ◽  
The Given

Human image generation is a very challenging task since it is affected by many factors. Many human image generation methods focus on generating human images conditioned on a given pose, while the generated backgrounds are often blurred. In this paper, we propose a novel Partition-Controlled GAN to generate human images according to target pose and background. Firstly, human poses in the given images are extracted, and foreground/background are partitioned for further use. Secondly, we extract and fuse appearance features, pose features and background features to generate the desired images. Experiments on Market-1501 and DeepFashion datasets show that our model not only generates realistic human images but also produce the human pose and background as we want. Extensive experiments on COCO and LIP datasets indicate the potential of our method.

Study on the Structural Model of Human Pose

2013 ◽  
Vol 464 ◽  
pp. 387-390
Author(s):  
Wei Hua Wang
Keyword(s):  
Computer Vision ◽  
Human Behavior ◽  
Structural Model ◽  
New Method ◽  
Domain Modeling ◽  
Key Technology ◽  
Broad Application ◽  
Structural Relation ◽  
Human Pose ◽  
Human Image

The analysis and understand of human behavior is broad application in the computer vision domain, modeling the human pose is one of the key technology. In order to simplify the model of the human pose and expediently describe the human pose, a lot of condition was appended to confine the process of human pose modeling or the application environments in the current research. In this paper, a new method for modeling the human pose was proposed. The human pose was modeled by the structural relation according to the physiological structural, the advantages of the model are the independent of move, the independent of scale of the human image and the dependent of view angle, it can be used to modeling the human behavior in video.

scholarly journals Deformable GANs for Pose-Based Human Image Generation

2018 ◽  
Author(s):  
Aliaksandr Siarohin ◽  
Enver Sangineto ◽  
Stephane Lathuiliere ◽  
Nicu Sebe
Keyword(s):  
Image Generation ◽  
Human Image

scholarly journals Multiscale Meets Spatial Awareness: An Efficient Attention Guidance Network for Human Parsing

2020 ◽  
Vol 2020 ◽  
pp. 1-12
Author(s):  
Fan Zhou ◽  
Enbo Huang ◽  
Zhuo Su ◽  
Ruomei Wang
Keyword(s):  
State Of The Art ◽  
Spatial Awareness ◽  
Significant Progress ◽  
Deep Convolutional Neural Networks ◽  
Edge Information ◽  
Comprehensive Evaluations ◽  
Human Pose ◽  
Human Image ◽  
Public Datasets ◽  
Spatial Semantics

Human parsing, which aims at resolving human body and clothes into semantic part regions from an human image, is a fundamental task in human-centric analysis. Recently, the approaches for human parsing based on deep convolutional neural networks (DCNNs) have made significant progress. However, hierarchically exploiting multiscale and spatial contexts as convolutional features is still a hurdle to overcome. In order to boost the scale and spatial awareness of a DCNN, we propose two effective structures, named “Attention SPP and Attention RefineNet,” to form a Mutual Attention operation, to exploit multiscale and spatial semantics different from the existing approaches. Moreover, we propose a novel Attention Guidance Network (AG-Net), a simple yet effective architecture without using bells and whistles (such as human pose and edge information), to address human parsing tasks. Comprehensive evaluations on two public datasets well demonstrate that the AG-Net outperforms the state-of-the-art networks.

Differentiable Rendering-based Pose-Conditioned Human Image Generation

2021 ◽  
Author(s):  
Yusuke Horiuchi ◽  
Edgar Simo-Serra ◽  
Satoshi Iizuka ◽  
Hiroshi Ishikawa
Keyword(s):  
Image Generation ◽  
Human Image

Perceptual metric-guided human image generation

2021 ◽  
pp. 1-11
Author(s):  
Haoran Wu ◽  
Fazhi He ◽  
Yansong Duan ◽  
Xiaohu Yan
Keyword(s):  
State Of The Art ◽  
Transfer Task ◽  
Generative Adversarial Networks ◽  
Perceptual Quality ◽  
Image Generation ◽  
Migration Process ◽  
Adversarial Networks ◽  
Human Image ◽  
Detection Score ◽  
Perceptual Metrics

Pose transfer, which synthesizes a new image of a target person in a novel pose, is valuable in several applications. Generative adversarial networks (GAN) based pose transfer is a new way for person re-identification (re-ID). Typical perceptual metrics, like Detection Score (DS) and Inception Score (IS), were employed to assess the visual quality after generation in pose transfer task. Thus, the existing GAN-based methods do not directly benefit from these metrics which are highly associated with human ratings. In this paper, a perceptual metrics guided GAN (PIGGAN) framework is proposed to intrinsically optimize generation processing for pose transfer task. Specifically, a novel and general model-Evaluator that matches well the GAN is designed. Accordingly, a new Sort Loss (SL) is constructed to optimize the perceptual quality. Morevover, PIGGAN is highly flexible and extensible and can incorporate both differentiable and indifferentiable indexes to optimize the attitude migration process. Extensive experiments show that PIGGAN can generate photo-realistic results and quantitatively outperforms state-of-the-art (SOTA) methods.

scholarly journals Appearance and Pose-Conditioned Human Image Generation using Deformable GANs

2019 ◽  
pp. 1-1 ◽  
Author(s):  
Aliaksandr Siarohin ◽  
Stephane Lathuiliere ◽  
Enver Sangineto ◽  
Nicu Sebe
Keyword(s):  
Image Generation ◽  
Human Image

scholarly journals A SURVEY OF METHODS OF TEXT-TO-IMAGE TRANSLATION

2019 ◽  
Vol 2 (93) ◽  
pp. 64-68
Author(s):  
I. Konarieva ◽  
D. Pydorenko ◽  
O. Turuta
Keyword(s):  
Generative Adversarial Networks ◽  
Text Compression ◽  
Image Generation ◽  
Adversarial Networks ◽  
Image Translation ◽  
Different Types ◽  
The Given

The given work considers the existing methods of text compression (finding keywords or creating summary) using RAKE, Lex Rank, Luhn, LSA, Text Rank algorithms; image generation; text-to-image and image-to-image translation including GANs (generative adversarial networks). Different types of GANs were described such as StyleGAN, GauGAN, Pix2Pix, CycleGAN, BigGAN, AttnGAN. This work aims to show ways to create illustrations for the text. First, key information should be obtained from the text. Second, this key information should be transformed into images. There were proposed several ways to transform keywords to images: generating images or selecting them from a dataset with further transforming like generating new images based on selected ow combining selected images e.g. with applying style from one image to another. Based on results, possibilities for further improving the quality of image generation were also planned: combining image generation with selecting images from a dataset, limiting topics of image generation.

Sign in / Sign up

Export Citation Format

Share Document