2019-yu.pdf: “Generating Furry Face Art from Sketches using a GAN”, Andrew Yu (2019-12-01):
I generate furry face artwork from color sketches. The sketches are procedurally generated from a data set of furry artwork. Sketches are translated back into artwork via a Generative Adversarial Network. I implement the GAN using a U-Net autoencoder with encoder-decoder skip connections and experiment with adding adaptive instance normalization into upsampling layers. The results show effective mapping of training and dev set sketches back to their input style. However, the model does not perform as effectively on novel user sketches and often fails to add stochastic textures like hair details.
2020-akita.pdf: “Deep-Eyes: Fully Automatic Anime Character Colorization with Painting of Details on Empty Pupils”, Kenta Akita, Yuki Morimoto, Reiji Tsuruno (2020-01-01):
Many studies have recently applied deep learning to the automatic colorization of line drawings. However, it is difficult to paint empty pupils using existing methods because the networks are trained with pupils that have edges, which are generated from color images using image processing. Most actual line drawings have empty pupils that artists must paint in. In this paper, we propose a novel network model that transfers the pupil details in a reference color image to input line drawings with empty pupils. We also propose a method for accurately and automatically coloring eyes. In this method, eye patches are extracted from a reference color image and automatically added to an input line drawing as color hints using our eye position estimation network.
2020-cao.pdf: “Deep learning-based classification of the polar emotions of 'moe'-style cartoon pictures”, Qinchen Cao, Weilin Zhang, Yonghua Zhu (2020-10-12):
The cartoon animation industry has developed into a huge industrial chain with a large potential market involving games, digital entertainment, and other industries. However, due to the coarse-grained classification of cartoon materials, cartoon animators can hardly find relevant materials during the process of creation. The polar emotions of cartoon materials are an important reference for creators as they can help them easily obtain the pictures they need. Some methods for obtaining the emotions of cartoon pictures have been proposed, but most of these focus on expression recognition. Meanwhile, other emotion recognition methods are not ideal for use as cartoon materials. We propose a deep learning-based method to classify the polar emotions of the cartoon pictures of the “Moe” drawing style. According to the expression feature of the cartoon characters of this drawing style, we recognize the facial expressions of cartoon characters and extract the scene and facial features of the cartoon images. Then, we correct the emotions of the pictures obtained by the expression recognition according to the scene features. Finally, we can obtain the polar emotions of corresponding picture. We designed a dataset and performed verification tests on it, achieving 81.9% experimental accuracy. The experimental results prove that our method is competitive. [Keywords: cartoon; emotion classification; deep learning]
2020-dragan.pdf: “Demonstrating that dataset domains are largely linearly separable in the feature space of common CNNs”, Matthew R. Dragan (2020-09-01):
Deep convolutional neural networks (DCNNs) have achieved state of the art performance on a variety of tasks. These high-performing networks require large and diverse training datasets to facilitate generalization when extracting high-level features from low-level data. However, even with the availability of these diverse datasets, DCNNs are not prepared to handle all the data that could be thrown at them.
One major challenges DCNNs face is the notion of forced choice. For example, a network trained for image classification is configured to choose from a predefined set of labels with the expectation that any new input image will contain an instance of one of the known objects. Given this expectation it is generally assumed that the network is trained for a particular domain, where domain is defined by the set of known object classes as well as more implicit assumptions that go along with any data collection. For example, some implicit characteristics of the ImageNet dataset domain are that most images are taken outdoors and the object of interest is roughly in the center of the frame. Thus the domain of the network is defined by the training data that is chosen.
Which leads to the following key questions:
- Does a network know the domain it was trained for? and
- Can a network easily distinguish between in-domain and out-of-domain images?
In this thesis it will be shown that for several widely used public datasets and commonly used neural networks, the answer to both questions is yes. The presence of a simple method of differentiating between in-domain and out-of-domain cases has substantial implications for work on domain adaptation, transfer learning, and model generalization.
2020-ko.pdf: “SickZil-Machine (SZMC): A Deep Learning Based Script Text Isolation System for Comics Translation”, U-Ram Ko, Hwan-Gue Cho (2020-08-14):
The translation of comics (and Manga) involves removing text from a foreign comic images and typesetting translated letters into it. The text in comics contain a variety of deformed letters drawn in arbitrary positions, in complex images or patterns. These letters have to be removed by experts, as computationally erasing these letters is very challenging. Although several classical image processing algorithms and tools have been developed, a completely automated method that could erase the text is still lacking. Therefore, we propose an image processing framework called ‘SickZil-Machine’ (SZMC) that automates the removal of text from comics. SZMC works through a two-step process. In the first step, the text areas are segmented at the pixel level. In the second step, the letters in the segmented areas are erased and inpainted naturally to match their surroundings. SZMC exhibited a notable performance, employing deep learning based image segmentation and image inpainting models. To train these models, we constructed 285 pairs of original comic pages, a text area-mask dataset, and a dataset of 31,497 comic pages. We identified the characteristics of the dataset that could improve SZMC performance. SZMC is available. [Keywords: comics translation, deep learning, image manipulation system]
2020-koyama.pdf: “System for searching illustrations of anime characters focusing on degrees of character attributes”, Yuta Koyama, Tomohiro Fukuhara, Koichi Yamada, Hironobu Abe, Hidetaka Masuda (2020-06-01):
Keyword searches are generally used when searching for illustrations of anime characters. However, keyword searches require that the illustrations be tagged first. The illustration information that a tag can express is limited, and it is difficult to search for a specific illustration. We focus on character attributes that are difficult to express using tags. We propose a new search method using the vectorization degrees of character attributes. Accordingly, we first created a character illustration dataset limited to the hair length attribute and then trained a convolutional neural network (CNN) to extract the features. We obtained a [illustration2vec Danbooru] vector representation of the character attributes using CNN and confirmed that they could be used for new searches. [Keywords: Illustration search, Anime characters, Vectorization, CNN]
2020-lee.pdf: “Automatic Colorization of Anime Style Illustrations Using a Two-Stage Generator”, LaTeX with hyperref package (2020-12-04):
Line-arts are used in many ways in the media industry. However, line-art colorization is tedious, labor-intensive, and time consuming. For such reasons, a Generative Adversarial Network (GAN)-based image-to-image colorization method has received much attention because of its promising results. In this paper, we propose to use color a point hinting method with two GAN-based generators used for enhancing the image quality. To improve the coloring performance of drawing with various line styles, generator takes account of the loss of the line-art. We propose a Line Detection Model (LDM) which is used in measuring line loss. LDM is a method of extracting line from a color image. We also propose histogram equalizer in the input line-art to generalize the distribution of line styles. This approach allows the generalization of the distribution of line style without increasing the complexity of inference stage. In addition, we propose seven segment hint pointing constraints to evaluate the colorization performance of the model with Fréchet Inception Distance (FID) score. We present visual and qualitative evaluations of the proposed methods. The result shows that using histogram equalization and LDM enabled line loss exhibits the best result. The Base model with XDoG (eXtended Difference-Of-Gaussians)generated line-art with and without color hints exhibits FID for colorized images score of 35.83 and 44.70, respectively, whereas the proposed model in the same scenario exhibits 32.16 and 39.77, respectively.
2020-wu.pdf: “Watermarking Neural Networks with Watermarked Images”, Hanzhou Wu, Gen Liu, Yuwei Yao, Xinpeng Zhang (2020-10-13):
Watermarking neural networks is a quite important means to protect the intellectual property (IP) of neural networks. In this paper, we introduce a novel digital watermarking framework suitable for deep neural networks that output images as the results, in which any image outputted from a watermarked neural network must contain a certain watermark. Here, the host neural network to be protected and a watermark-extraction network are trained together, so that, by optimizing a combined loss function, the trained neural network can accomplish the original task while embedding a watermark into the outputted images. This work is totally different from previous schemes carrying a watermark by network weights or classification labels of the trigger set. By detecting watermarks in the outputted images, this technique can be adopted to identify the ownership of the host network and find whether an image is generated from a certain neural network or not. We demonstrate that this technique is effective and robust on a variety of image processing tasks, including image colorization, super-resolution, image editing, semantic segmentation and so on. [Keywords: watermarking, neural networks, deep learning, image transformation, information hiding]
2020-zheng.pdf: “Learning from the Past: Meta-Continual Learning with Knowledge Embedding for Jointly Sketch, Cartoon, and Caricature Face Recognition”, Wenbo Zheng, Lan Yan, Fei-Yue Wang, Chao Gou (2020-10):
This paper deals with a challenging task of learning from different modalities by tackling the difficulty problem of jointly face recognition between abstract-like sketches, cartoons, caricatures and real-life photographs. Due to the substantial variations in the abstract faces, building vision models for recognizing data from these modalities is an extremely challenging. We propose a novel framework termed as Meta-Continual Learning with Knowledge Embedding to address the task of jointly sketch, cartoon, and caricature face recognition. In particular, we firstly present a deep relational network to capture and memorize the relation among different samples. Secondly, we present the construction of our knowledge graph that relates image with the label as the guidance of our meta-learner. We then design a knowledge embedding mechanism to incorporate the knowledge representation into our network. Thirdly, to mitigate catastrophic forgetting, we use a meta-continual model that updates our ensemble model and improves its prediction accuracy. With this meta-continual model, our network can learn from its past. The final classification is derived from our network by learning to compare the features of samples. Experimental results demonstrate that our approach achieves substantially higher performance compared with other state-of-the-art approaches.
2021-fang.pdf: “Stylized–Colorization for Line Arts”, Tzu-Ting Fang, Minh Duc Vo, Akihiro Sugimoto, Shang-Hong Lai (2021-01-10):
We address a novel problem of stylized-colorization which colorizes a given line art using a given coloring style in text. This problem can be stated as multi-domain image translation and is more challenging than the current colorization problem because it requires not only capturing the illustration distribution but also satisfying the required coloring styles specific to anime such as lightness, shading, or saturation. We propose a GAN-based end-to-end model for stylized-colorization where the model has one generator and two discriminators. Our generator is based on the U-Net architecture and receives a pair of a line art and a coloring style in text as its input to produce a stylized-colorization image of the line art. Two discriminators, on the other hand, share weights at early layers to judge the stylized-colorization image in two different aspects: one for color and one for style. One generator and two discriminators are jointly trained in an adversarial and end-to-end manner. Extensive experiments demonstrate the effectiveness of our proposed model.