Filters








2,030 Hits in 4.0 sec

Pastiche Master: Exemplar-Based High-Resolution Portrait Style Transfer [article]

Shuai Yang, Liming Jiang, Ziwei Liu, Chen Change Loy
2022 arXiv   pre-print
Recent studies on StyleGAN show high performance on artistic portrait generation by transfer learning with limited data.  ...  In this paper, we explore more challenging exemplar-based high-resolution portrait style transfer by introducing a novel DualStyleGAN with flexible control of dual styles of the original face domain and  ...  We further collect datasets in styles of Pixar, Comic and Slam Dunk from the Internet, with 122, 101 and 120 images, respectively.  ... 
arXiv:2203.13248v1 fatcat:pc2wurrfyvb2rmpsec425x3omi

A Foreground-Aware Framework for Local Face Attribute Transfer

Yuanbin Fu, Jiayi Ma, Xiaojie Guo
2021 Entropy  
Though there are many algorithms automatically and globally transferring the style from one image to another, they fail to respect the semantics of the scene and are unable to allow users to merely transfer  ...  To overcome this problem, we developed a novel framework for semantically meaningful local face attribute transfer, which can flexibly transfer the local attribute of a face organ from the reference image  ...  With the guidance of a semantic map, Luan et al.  ... 
doi:10.3390/e23050615 pmid:34065640 pmcid:PMC8156749 fatcat:iy24mqqjurfdbmhidu2yq3gvri

Estimation of Semantic Impressions from Portraits

Mari MIYATA, Kiyoharu AIZAWA
2021 IEICE transactions on information and systems  
a portrait.  ...  In the second part, we leveraged the knowledge from the results of the analysis to develop a ranking network trained on the collected data and designed to estimate the semantic impression associated with  ...  Rule-based and/or sample-based methods are frequently used to generate new portraits for purposes such as makeup style transfer [6] , [32] , [33] and facial image editing based on attributes [12]  ... 
doi:10.1587/transinf.2020edp7140 fatcat:z7xtllxlsfebnd5a742yfc43em

Uncouple Generative Adversarial Networks for Transferring Stylized Portraits to Realistic Faces

Wenxiao Wang, Hon-Cheng Wong, Sio-Long Lo, Guifang Zhang
2020 IEEE Access  
For y  , we selected the Color Pencil Sketch Gallery [3] and collected images from the internet according to the experimental requirements to establish a self-built new dataset.  ...  We only chose color pencil sketch portraits, and allowed images for random flips, and adapted the input adjustments to hue, brightness, and saturation.  ... 
doi:10.1109/access.2020.3039969 fatcat:tcqa3p5jancjffeo3y7bgb5nxq

StyleRig: Rigging StyleGAN for 3D Control over Portrait Images [article]

Ayush Tewari, Mohamed Elgharib, Gaurav Bharaj, Florian Bernard, Hans-Peter Seidel, Patrick Pérez, Michael Zollhöfer, Christian Theobalt
2020 arXiv   pre-print
At test time, our method generates portrait images with the photorealism of StyleGAN and provides explicit control over the 3D semantic parameters of the face.  ...  StyleGAN generates photorealistic portrait images of faces with eyes, teeth, hair and context (neck, shoulders, background), but lacks a rig-like control over semantic face parameters that are interpretable  ...  Cycle-Consistent Per-Pixel Editing Loss Given two latent codes, w and v with corresponding images I w and I v , we transfer the semantic parameters of v to w during training.  ... 
arXiv:2004.00121v2 fatcat:4bpgows3czdjvkbeu2l6autmou

Progressive Color Transfer with Dense Semantic Correspondences [article]

Mingming He, Jing Liao, Dongdong Chen, Lu Yuan, Pedro V. Sander
2018 arXiv   pre-print
We propose a new algorithm for color transfer between images that have perceptually similar semantic structures.  ...  We aim to achieve a more accurate color transfer that leverages semantically-meaningful dense correspondence between images.  ...  Our color transfer is suitable for semantically similar images.  ... 
arXiv:1710.00756v2 fatcat:vlkbf4lyv5fjfjas7cuu5v3kce

SSH: A Self-Supervised Framework for Image Harmonization [article]

Yifan Jiang, He Zhang, Jianming Zhang, Yilin Wang, Zhe Lin, Kalyan Sunkavalli, Simon Chen, Sohrab Amirghodsi, Sarah Kong, Zhangyang Wang
2021 arXiv   pre-print
This framework design allows for a dual data augmentation method, where diverse [foreground, background, pseudo GT] triplets can be generated by cropping an image with perturbations using 3D color lookup  ...  Image harmonization aims to improve the quality of image compositing by matching the "appearance" (, color tone, brightness and contrast) between foreground and background images.  ...  with simple color-transfer methods [29, 35, 8, 28] .  ... 
arXiv:2108.06805v2 fatcat:i7a5rfypmbg7rm2abf6zpvfhxi

Single-view hair modeling for portrait manipulation

Menglei Chai, Lvdi Wang, Yanlin Weng, Yizhou Yu, Baining Guo, Kun Zhou
2012 ACM Transactions on Graphics  
It also enables several interesting applications such as transferring the hairstyle of one subject to another (e). Original images courtesy of Getty Images (a) and Andrew MacPherson (e).  ...  , rendering the original portrait in a novel view and image-space hair editing.  ...  We would like to thank Xin Tong for helpful discussions, the SIG-GRAPH reviewers for their constructive comments, and the image owners for letting us use their work.  ... 
doi:10.1145/2185520.2335467 fatcat:snlc7mstznegxfnkvjpuoiflau

Single-view hair modeling for portrait manipulation

Menglei Chai, Lvdi Wang, Yanlin Weng, Yizhou Yu, Baining Guo, Kun Zhou
2012 ACM Transactions on Graphics  
It also enables several interesting applications such as transferring the hairstyle of one subject to another (e). Original images courtesy of Getty Images (a) and Andrew MacPherson (e).  ...  , rendering the original portrait in a novel view and image-space hair editing.  ...  We would like to thank Xin Tong for helpful discussions, the SIG-GRAPH reviewers for their constructive comments, and the image owners for letting us use their work.  ... 
doi:10.1145/2185520.2185612 fatcat:wb3pik7qtffpnp3mpk4vlythxm

Quality Metric Guided Portrait Line Drawing Generation from Unpaired Training Data

Ran Yi, Yong-Jin Liu, Yu-Kun Lai, Paul Rosin
2022 IEEE Transactions on Pattern Analysis and Machine Intelligence  
However, due to its high semantic constraints, many existing methods learn to generate portrait drawings using paired training data.  ...  Along with localized discriminators for important facial regions, our method well preserves all important facial features.  ...  First, artistic portrait line drawings (APDrawings) are quite different from the previously tackled image styles. Image style transfer has been a longstanding topic in computer vision.  ... 
doi:10.1109/tpami.2022.3147570 pmid:35104210 fatcat:owiyzlthwvcyhfahi36qb4wfg4

Example-Guided Style-Consistent Image Synthesis From Semantic Labeling

Miao Wang, Guo-Ye Yang, Ruilong Li, Run-Ze Liang, Song-Hai Zhang, Peter M. Hall, Shi-Min Hu
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Abstract Example-guided image synthesis aims to synthesize an image from a semantic label map and an exemplary image indicating style.  ...  Figure 1 : We present a generative adversarial framework for synthesizing images from semantic label maps as well as image exemplars.  ...  While the pix2pixHD is able to generate photorealistic images consistent with the input semantic labels, it is not able to keep the style (e.g. gender, hair, skin color) from input exemplars in the synthetic  ... 
doi:10.1109/cvpr.2019.00159 dblp:conf/cvpr/0004YLLZHH19 fatcat:plmskjeagbasbcxcoaz3fwsfsa

Example-Based Image Colorization Using Locality Consistent Sparse Representation

Bo Li, Fuchen Zhao, Zhuo Su, Xiangguo Liang, Yu-Kun Lai, Paul L. Rosin
2017 IEEE Transactions on Image Processing  
Image colorization aims to produce a natural looking color image from a given grayscale image, which remains a challenging problem.  ...  Finally, to further improve coherence while preserving sharpness, we develop a new edge-preserving filter for chrominance channels with the guidance from the target grayscale image.  ...  We also want to thank the authors of [34] - [37] for providing the codes for image color transfer.  ... 
doi:10.1109/tip.2017.2732239 pmid:28749352 fatcat:lga35cjajje6lkvqlarqjjf6my

Adaptive color transfer from images to terrain visualizations [article]

Mingguang Wu, Yanjie Sun, Shangjing Jiang
2022 arXiv   pre-print
In this paper, we present a two-step image-to-terrain color transfer method that can transfer color from arbitrary images to diverse terrain models.  ...  We also define color similarity between image and terrain visualization with aesthetic quality.  ...  Results of transfer color from van Gogh's two paintings: (a) self-portrait; and (b) irises. First , we present a new image color organization method.  ... 
arXiv:2205.14908v1 fatcat:qto2gvgnjfdh7pmgvpkxkt4poy

Internet visual media processing: a survey with graphics and vision applications

Shi-Min Hu, Tao Chen, Kun Xu, Ming-Ming Cheng, Ralph R. Martin
2013 The Visual Computer  
In recent years, the computer graphics and computer vision communities have devoted significant attention to research based on Internet visual media resources.  ...  This article surveys recent research as regards processing of large collections of images and video, including work on analysis, manipulation, and synthesis.  ...  The system then uses Internet images to find the best matches for color transfer.  ... 
doi:10.1007/s00371-013-0792-6 fatcat:omwwludvznhvrmgl5oeffienyy

Steganography for Retinal Biometrics

2019 VOLUME-8 ISSUE-10, AUGUST 2019, REGULAR ISSUE  
Retinal scanners use infrared rays along with non-invasive color retinal cameras and are very effective in getting a retinal image.  ...  After getting the retinal details, steganographic methods are used to transfer this file securely over the internet. Once received at the receiver, it can be used for verification of user authenticity  ...  We embed color retinal secret image into a colored cover image. Using cryptography along with steganography enhances the security.  ... 
doi:10.35940/ijitee.b6497.129219 fatcat:uyyrwgxfzjgrhd4szjdkue5icq
« Previous Showing results 1 — 15 out of 2,030 results