Blending texture features from multiple reference images for style transfer

Ikuta, Hikaru; Ogaki, Keisuke; Odagiri, Yuri

doi:10.1145/3005358.3005388

Cited by 9 publications

(6 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the amateur-level dataset, we used illustrations with nico-opendata [14] tags of "girl" or "boy" and with a five or less bookmark count. Similar to the professional-level dataset, we used extracted faces of the characters for the amateur-level dataset.…”

Section: Methodsmentioning

confidence: 99%

Improving The Quality Of Illustrations: Transforming Amateur Illustrations To A Professional Standard

Awane¹,

Tsubota

Ikuta

et al. 2021

2021 IEEE International Conference on Image Processing (ICIP)

Self Cite

View full text Add to dashboard Cite

We propose an amateur-to professional-level illustration translator that can modify amateur illustrations slightly to produce professional-level quality images. The proposed translator is a GAN-based image translation module. We focus only on the neighboring region of a contour to improve the quality of the illustration by applying image completion to the neighboring region of the extracted line drawing. We artificially augment amateur-level illustrations from professional-level illustrations to solve the lack of a pair of amateur-level and professional-level datasets. This enables us to automatically prepare a pair of amateur-level and professional-level images, through which we can train a translator network. Through experiments and user study, we show that the proposed method improves the quality of amateur illustrations.

show abstract

Section: Methodsmentioning

confidence: 99%

Improving The Quality Of Illustrations: Transforming Amateur Illustrations To A Professional Standard

Awane¹,

Tsubota

Ikuta

et al. 2021

2021 IEEE International Conference on Image Processing (ICIP)

Self Cite

View full text Add to dashboard Cite

show abstract

“…In the first step, we collected Anime art-style images from Nico-illust [7], a community illustration from Niconico Seiga and Niconico Shunga, for training, validating, and testing sets. The collected images, which are a JPG format, are split into 160 images for a training set, 20 images for validation, and 20 images for a testing set.…”

Section: A Data Collectionmentioning

confidence: 99%

“…Finally, we tested our methods with Nico-illust dataset [7] and evaluated the performance by using the PSNR and SSIM metrics. Results show that our models can outperform the conventional SRCNN and other baseline methods in most cases.…”

Section: Introductionmentioning

confidence: 99%

Enhancement of Anime Imaging Enlargement using Modified Super-Resolution CNN

Intaniyom¹,

Thananporn²,

Woraratpanya³

2021

Preprint

View full text Add to dashboard Cite

Anime is a storytelling medium similar to movies and books. Anime images are a kind of artworks, which are almost entirely drawn by hand. Hence, reproducing existing Anime with larger sizes and higher quality images is expensive. Therefore, we proposed a model based on convolutional neural networks to extract outstanding features of images, enlarge those images, and enhance the quality of Anime images. We trained the model with a training set of 160 images and a validation set of 20 images. We tested the trained model with a testing set of 20 images. The experimental results indicated that our model successfully enhanced the image quality with a larger image-size when compared with the common existing image enlargement and the original SRCNN method.

show abstract

“…They are asked to trace lines of a given cartoon image using a drawing tablet. We use the illustrations from the Nico-Illust dataset [IOO16], which is an open dataset containing over 400,000 images. To enhance the data variety and tolerability to background regions, we intentionally select images that contain cluttered background, and the line tracing process focuses on those significant edges.…”

Section: Line Tracing Datasetmentioning

confidence: 99%