Photo-sketch Pairs Research Articles

Semi-supervised Cycle-GAN for face photo-sketch translation in the wild

The performance of face photo-sketch translation has improved a lot thanks to deep neural networks. GAN based methods trained on paired images can produce high-quality results under laboratory settings. Such paired datasets are, however, often very small and lack diversity. Meanwhile, Cycle-GANs trained with unpaired photo-sketch datasets suffer from the steganography phenomenon, which makes them not effective to face photos in the wild. In this paper, we introduce a semi-supervised approach with a noise-injection strategy, named Semi-Cycle-GAN (SCG), to tackle these problems. For the first problem, we propose a pseudo sketch feature representation for each input photo composed from a small reference set of photo-sketch pairs, and use the resulting pseudo pairs to supervise a photo-to-sketch generator Gp2s. The outputs of Gp2s can in turn help to train a sketch-to-photo generator Gs2p in a self-supervised manner. This allows us to train Gp2s and Gs2p using a small reference set of photo-sketch pairs together with a large face photo dataset (without ground-truth sketches). For the second problem, we show that the simple noise-injection strategy works well to alleviate the steganography effect in SCG and helps to produce more reasonable sketch-to-photo results with less overfitting than fully supervised approaches. Experiments show that SCG achieves competitive performance on public benchmarks and superior results on photos in the wild.

Unsupervised self-attention lightweight photo-to-sketch synthesis with feature maps

Face-sketch synthesis is important for gaining a clear portrait photo of suspects when solving crimes. Recent research has made a great process in self-attention generative adversarial networks. We propose a method of unsupervised learning in the synthesis of face sketch-to-photo using a new attention module. The method of processing on a small reference set of photo-sketch pairs adds to the attention module, a focus on the regions distinguishing photos from sketches on the basis of the feature maps obtained by the auxiliary classifier. Unlike previous attention-based methods, which cannot handle the geometric changes between domains, our model can translate images requiring holistic changes. At the same time, we reduce the layers of the discriminator according to different residual layers to optimize our network. With the proposed approach, we can train our networks using a small reference set of photo-sketch pairs together with a large number of face-photo datasets and more distinguishing facial-feature regions in the self-attention model. Experiments have shown the superiority of the proposed method to existing face sketch-to-photo synthesis models using fixed network architectures and hyper-parameters.

Knowledge Distillation for Face Photo-Sketch Synthesis.

Significant progress has been made with face photo-sketch synthesis in recent years due to the development of deep convolutional neural networks, particularly generative adversarial networks (GANs). However, the performance of existing methods is still limited because of the lack of training data (photo-sketch pairs). To address this challenge, we investigate the effect of knowledge distillation (KD) on training neural networks for the face photo-sketch synthesis task and propose an effective KD model to improve the performance of synthetic images. In particular, we utilize a teacher network trained on a large amount of data in a related task to separately learn knowledge of the face photo and knowledge of the face sketch and simultaneously transfer this knowledge to two student networks designed for the face photo-sketch synthesis task. In addition to assimilating the knowledge from the teacher network, the two student networks can mutually transfer their own knowledge to further enhance their learning. To further enhance the perception quality of the synthetic image, we propose a KD+ model that combines GANs with KD. The generator can produce images with more realistic textures and less noise under the guide of knowledge. Extensive experiments and a user study demonstrate the superiority of our models over the state-of-the-art methods.

Cross-Domain Face Sketch Synthesis

Synthesizing sketches from facial photos is of great significance to digital entertainment. Along with higher demands on sketch quality in a complex environment, however, it has been an urgent issue on how to synthesize realistic sketches with the limited training data. The existing face sketch methods pay less attention to the insufficient problem of the training data, leading to the synthesized sketches with some noise or without some identity-specific information in real-world applications. Target on providing sufficient photo-sketch pairs to meet the demand of users in digital entertainment, we present a cross-domain face sketch synthesis framework in this paper. In the photo-sketch mixed domain, we leverage the generative adversarial network to construct a cross-domain mapping function and generate identity-preserving face sketches as the hidden training data. Combined it with the insufficient original training data, we provide sufficient training data to recover the underlying structures and learn the cross-domain transfer of the high-level qualitative knowledge from the photo domain to the sketch domain by the latent low-rank representation. The qualitative and quantitative evaluations on the public facial photo-sketch database demonstrate that the proposed cross-domain face sketch synthesis method can solve the insufficient problem of the training data successfully. And it outperforms other state-of-the-art works and generates more vivid and cleaner facial sketches.

Markov random fields and facial landmarks for handling uncontrolled images of face sketch synthesis

Face sketch synthesis has drawn great attention in many computer vision applications such as law enforcement and digital entertainment. The majority of existing face sketch synthesis techniques are exemplar-based techniques, where a set of training photo–sketch pairs are first divided into patches. For an input photo patch from the face to be synthesized, k similar photo patches are found from the training set. The corresponding sketch patch of the best match is then selected to be synthesized. In such techniques, a multiscale Markov random fields (MRF) model is utilized for synthesizing a sketch using candidate sketch patches; having observed that techniques tend to fail with face photos acquired in uncontrolled imaging conditions like pose and lighting variations. For example, some structures along the lower part of the face sketch contour get lost due to ignoring the global face shape information and illumination changes. In this paper, we propose a reliable face sketch synthesis method based on MRF model and facial landmarks, called MRF-FL that can maintain further structures with uncontrolled face photos. Besides matching the input photo with training photo, the input photo and training sketch are also matched based on the facial landmarks so as to enhance face sketch structures around the lower part of face sketch contour. Experimental results showed that the proposed MRF-FL achieves superior performance compared with recent face sketch synthesis methods on CUHK and AR face sketch databases.

Face Sketch Synthesis by Multidomain Adversarial Learning.

Given a training set of face photo-sketch pairs, face sketch synthesis targets at learning a mapping from the photo domain to the sketch domain. Despite the exciting progresses made in the literature, it retains as an open problem to synthesize high-quality sketches against blurs and deformations. Recent advances in generative adversarial training provide a new insight into face sketch synthesis, from which perspective the existing synthesis pipelines can be fundamentally revisited. In this paper, we present a novel face sketch synthesis method by multidomain adversarial learning (termed MDAL), which overcomes the defects of blurs and deformations toward high-quality synthesis. The principle of our scheme relies on the concept of "interpretation through synthesis." In particular, we first interpret face photographs in the photodomain and face sketches in the sketch domain by reconstructing themselves respectively via adversarial learning. We define the intermediate products in the reconstruction process as latent variables, which form a latent domain. Second, via adversarial learning, we make the distributions of latent variables being indistinguishable between the reconstruction process of the face photograph and that of the face sketch. Finally, given an input face photograph, the latent variable obtained by reconstructing this face photograph is applied for synthesizing the corresponding sketch. Quantitative comparisons to the state-of-the-art methods demonstrate the superiority of the proposed MDAL method.

Deep Neural Representation Guided Face Sketch Synthesis.

Face sketch synthesis shows great applications in a lot of fields such as online entertainment and suspects identification. Existing face sketch synthesis methods learn the patch-wise sketch style from the training dataset containing photo-sketch pairs. These methods manipulate the whole process directly in the field of RGB space, which unavoidably results in unsmooth noises at patch boundaries. If denoising methods are used, the sketch edges would be blurred and face structures could not be restored. Recent researches of feature maps, which are the outputs of a certain neural network layer, have achieved great success in texture synthesis and artistic image generation. In this paper, we reformulate the face sketch synthesis problem into a neural network feature maps based optimization task. Our results accurately capture the sketch drawing style and make full use of the whole stylistic information hidden in the training dataset. Unlike former feature map based methods, we utilize the Enhanced 3D PatchMatch and cross-layer cost aggregation methods to obtain the target feature maps for the final results. Multiple experiments have shown that our approach imitates hand-drawn sketch style vividly, and has high-quality visual effects on CUHK, AR, XM2VTS and CUFSF face sketch datasets.

Face Sketch Synthesis From a Single Photo–Sketch Pair

Face sketch synthesis is crucial in many practical applications, such as digital entertainment and law enforcement. Previous methods relying on many photo–sketch pairs have made great progress. State-of-the-art face sketch synthesis algorithms adopt Bayesian inference (BI) (e.g., Markov random fields) to select local sketch patches around corresponding position from a set of training data. However, these methods have two limitations: 1) they depend on many training photo–sketch pairs and 2) they cannot tackle nonfacial factors (e.g., hairpins, glasses, backgrounds, and image size) if these factors are excluded in training data. In this paper, we propose a novel face sketch synthesis method that is capable of handling nonfacial factors only using a single photo–sketch pair from coarse to fine. Our method proposes a cascaded image synthesis (CIS) strategy and integrates sparse representation-based greedy search (SRGS) and BI for face sketch synthesis. We first apply SRGS to select candidate sketch patches from the whole training photo–sketch pairs sampled from the only photo–sketch pair. We then employ BI to estimate an initial sketch. Afterward, the input photo and the estimated initial sketch are taken as an additional photo–sketch pair for training. Finally, we adopt CIS with the given two photo–sketch pairs to further improve the quality of the initial sketch. The experimental results on several databases demonstrate that our algorithm outperforms state-of-the-art methods.

Robust Face Sketch Style Synthesis

Heterogeneous image conversion is a critical issue in many computer vision tasks, among which example-based face sketch style synthesis provides a convenient way to make artistic effects for photos. However, existing face sketch style synthesis methods generate stylistic sketches depending on many photo-sketch pairs. This requirement limits the generalization ability of these methods to produce arbitrarily stylistic sketches. To handle such a drawback, we propose a robust face sketch style synthesis method, which can convert photos to arbitrarily stylistic sketches based on only one corresponding template sketch. In the proposed method, a sparse representation-based greedy search strategy is first applied to estimate an initial sketch. Then, multi-scale features and Euclidean distance are employed to select candidate image patches from the initial estimated sketch and the template sketch. In order to further refine the obtained candidate image patches, a multi-feature-based optimization model is introduced. Finally, by assembling the refined candidate image patches, the completed face sketch is obtained. To further enhance the quality of synthesized sketches, a cascaded regression strategy is adopted. Compared with the state-of-the-art face sketch synthesis methods, experimental results on several commonly used face sketch databases and celebrity photos demonstrate the effectiveness of the proposed method.

Face sketch synthesis via sparse representation-based greedy search.

Face sketch synthesis has wide applications in digital entertainment and law enforcement. Although there is much research on face sketch synthesis, most existing algorithms cannot handle some nonfacial factors, such as hair style, hairpins, and glasses if these factors are excluded in the training set. In addition, previous methods only work on well controlled conditions and fail on images with different backgrounds and sizes as the training set. To this end, this paper presents a novel method that combines both the similarity between different image patches and prior knowledge to synthesize face sketches. Given training photo-sketch pairs, the proposed method learns a photo patch feature dictionary from the training photo patches and replaces the photo patches with their sparse coefficients during the searching process. For a test photo patch, we first obtain its sparse coefficient via the learnt dictionary and then search its nearest neighbors (candidate patches) in the whole training photo patches with sparse coefficients. After purifying the nearest neighbors with prior knowledge, the final sketch corresponding to the test photo can be obtained by Bayesian inference. The contributions of this paper are as follows: 1) we relax the nearest neighbor search area from local region to the whole image without too much time consuming and 2) our method can produce nonfacial factors that are not contained in the training set and is robust against image backgrounds and can even ignore the alignment and image size aspects of test photos. Our experimental results show that the proposed method outperforms several state-of-the-arts in terms of perceptual and objective metrics.

Image-based facial sketch-to-photo synthesis via online coupled dictionary learning

Image-based sketch-to-photo synthesis has received intense attention in recent years because of its potential applications in digital entertainment and law enforcement. In order to achieve successful hallucinating synthesis of a realistic face photo, a coupled dictionary is first learned from a set of training photo-sketch pairs for modeling the relationship between patches from sketches and photos. Then, a series of overlapped photo patches can be synthesized on the basis of the learned coupled dictionary. Afterwards, these overlapped photo patches are further selected by the proposed global energy minimization framework based on a Markov network. Finally, a multi-band blending process is carried out to synthesize a realistic face photo. The experimental results convincingly validate the effectiveness of the proposed approach in comparison with the existing techniques.

Face Photo-Sketch Synthesis and Recognition

In this paper, we propose a novel face photo-sketch synthesis and recognition method using a multiscale Markov Random Fields (MRF) model. Our system has three components: 1) given a face photo, synthesizing a sketch drawing; 2) given a face sketch drawing, synthesizing a photo; and 3) searching for face photos in the database based on a query sketch drawn by an artist. It has useful applications for both digital entertainment and law enforcement. We assume that faces to be studied are in a frontal pose, with normal lighting and neutral expression, and have no occlusions. To synthesize sketch/photo images, the face region is divided into overlapping patches for learning. The size of the patches decides the scale of local face structures to be learned. From a training set which contains photo-sketch pairs, the joint photo-sketch model is learned at multiple scales using a multiscale MRF model. By transforming a face photo to a sketch (or transforming a sketch to a photo), the difference between photos and sketches is significantly reduced, thus allowing effective matching between the two in face sketch recognition. After the photo-sketch transformation, in principle, most of the proposed face photo recognition approaches can be applied to face sketch recognition in a straightforward way. Extensive experiments are conducted on a face sketch database including 606 faces, which can be downloaded from our Web site (http://mmlab.ie.cuhk.edu.hk/facesketch.html).