Content-Adaptive Sketch Portrait Generation by Decompositional Representation Learning

Zhang, Dongyu; Lin, Liang; Chen, Tianshui; Wang, Xian; Tan, Wenan; Izquierdo, Ebroul

doi:10.1109/tip.2016.2623485

Cited by 47 publications

(26 citation statements)

References 38 publications

(62 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our work on sketch generation is closest to those based on style-transfer because both methods use end-to-end training of neural networks without the need for extensive data. Supervised learning methods like [1,14,13,21,18,25,26,24,19,17,4] learn from large sets of paired data and are directed towards producing handdrawn sketches, and are therefore not directly related to our work.…”

Section: Related Workmentioning

confidence: 99%

Stylized Sketch Generation using Convolutional Networks

Hemani¹,

Sinha²,

Krishnamurthy³

2019

Computer Science Research Notes

View full text Add to dashboard Cite

The task of synthesizing sketches from photographs has been pursued with image processing methods and supervised learning based approaches. The former lack flexibility and the latter require large quantities of ground-truth data which is hard to obtain because of the manual effort required. We present a convolutional neural network based framework for sketch generation that does not require ground-truth data for training and produces various styles of sketches. The method combines simple analytic loss functions that correspond to characteristics of the sketch. The network is trained on and evaluated for human face images. Several stylized variations of sketches are obtained by varying the parameters of the loss functions. The paper also discusses the implicit abstraction afforded by the deep convolutional network approach which results in high quality sketch output.

show abstract

Section: Related Workmentioning

confidence: 99%

Stylized Sketch Generation using Convolutional Networks

Hemani¹,

Sinha²,

Krishnamurthy³

2019

Computer Science Research Notes

View full text Add to dashboard Cite

show abstract

“…Few works have considered the use of deep learning for face photo-sketch synthesis and recognition, most notable being the approaches in [24]- [27]. However, these systems generally use relatively shallow networks or are primarily trained using images residing in a single modality (typically face photos).…”

Section: Related Workmentioning

confidence: 99%

Forensic Face Photo-Sketch Recognition Using a Deep Learning-Based Architecture

Galea

Farrugia

2017

IEEE Signal Process. Lett.

View full text Add to dashboard Cite

Numerous methods that automatically identify subjects depicted in sketches as described by eyewitnesses have been implemented, but their performance often degrades when using real-world forensic sketches and extended galleries that mimic law enforcement mug-shot galleries. Moreover, little work has been done to apply deep learning for face photo-sketch recognition despite its success in numerous application domains including traditional face recognition. This is primarily due to the limited number of sketch images available, which are insufficient to robustly train large networks. This letter aims to tackle these issues with the following contributions: 1) a state-of-the-art model pre-trained for face photo recognition is tuned for face photo-sketch recognition by applying transfer learning, 2) a three-dimensional morphable model is used to synthesise new images and artificially expand the training data, allowing the network to prevent over-fitting and learn better features, 3) multiple synthetic sketches are also used in the testing stage to improve performance, and 4) fusion of the proposed method with a state-of-the-art algorithm is shown to further boost performance. An extensive evaluation of several popular and state-of-the-art algorithms is also performed using publicly available datasets, thereby serving as a benchmark for future algorithms. Compared to a leading method, the proposed framework is shown to reduce the error rate by 80.7% for viewed sketches and lowers the mean retrieval rank by 32.5% for real-world forensic sketches.

show abstract

“…Face-to-sketch translation is quite challenging due to the fact that it is a non-linear process conditioned on the appearance of the input face. To address this problem, several methods have been proposed [35], [47], [50], [44], [15] for image-to-image translation problems which convert a photo to a sketch. However, these works focus only on the faceto-sketch-translation ignoring the possibility of using facial Fig.…”

Section: Introductionmentioning

confidence: 99%

Attribute-Guided Sketch Generation

Tang

Chen

Wang

et al. 2019

2019 14th IEEE International Conference on Automatic Face &Amp; Gesture Recognition (FG 2019)

View full text Add to dashboard Cite

Facial attributes are important since they provide a detailed description and determine the visual appearance of human faces. In this paper, we aim at converting a face image to a sketch while simultaneously generating facial attributes. To this end, we propose a novel Attribute-Guided Sketch Generative Adversarial Network (ASGAN) which is an endto-end framework and contains two pairs of generators and discriminators, one of which is used to generate faces with attributes while the other one is employed for image-to-sketch translation. The two generators form a W-shaped network (Wnet) and they are trained jointly with a weight-sharing constraint. Additionally, we also propose two novel discriminators, the residual one focusing on attribute generation and the triplex one helping to generate realistic looking sketches. To validate our model, we have created a new large dataset with 8,804 images, named the Attribute Face Photo & Sketch (AFPS) dataset which is the first dataset containing attributes associated to face sketch images. The experimental results demonstrate that the proposed network (i) generates more photo-realistic faces with sharper facial attributes than baselines and (ii) has good generalization capability on different generative tasks.

show abstract

Content-Adaptive Sketch Portrait Generation by Decompositional Representation Learning

Cited by 47 publications

References 38 publications

Stylized Sketch Generation using Convolutional Networks

Stylized Sketch Generation using Convolutional Networks

Forensic Face Photo-Sketch Recognition Using a Deep Learning-Based Architecture

Attribute-Guided Sketch Generation

Contact Info

Product

Resources

About