A curated list of awesome machine learning resources related to anime, manga and so on.
Sharing, suggestions and contributions are always welcome. Please take a look at the Contribution Guidelines first.
Also you can take a look at some realted news reports & blog posts for reference.
- MANPU - International Workshop on coMics ANalysis, Processing and Understanding
- SIG2D - SIG2D (Special Interest Group on 2D Information Processing; しぐつーでぃー) は,二次元情報処理に強い興味を持つ研究者・技術者によるグループである
- Publications: Publications - SIG2D
- anime_faces (scrapy) - The scrapy script for processing anime characters faces
- DANBOORU2017 - A Large-scale crowsourced and tagged anime illustration dataset
- eBDtheque - 100 images with ground truth for panels, speech balloons, tails, text lines, leading characters
- Manga109 - Over 20 thousand images of 109 volumes (21,142 images)
- IllustrationGAN - A simple, clean TensorFlow implementation of Generative Adversarial Networks with a focus on modeling illustrations
- Tensorflow-ACGAN-Anime-Generation - Tensorflow implementation of "Towards the Automatic Anime Characters Creation with Generative Adversarial Networks" which related to make.girls.moe
- animeGAN - A simple PyTorch Implementation of Generative Adversarial Networks, focusing on anime face drawing
- GirlsManifold - An attempt to replicate make.girls.moe using PyTorch
- Face Detection and Face Recognition of Cartoon Characters Using Feature Extraction Proceedings of IIEEJ Image Electronics and Visual Computing Workshop
- Manga FaceNet: Face Detection in Manga based on Deep Neural Network ICMR '17 Proceedings of the 2017 ACM on International Conference on Multimedia Retrieva
- Pose estimation of anime/manga characters: a case for synthetic data MANPU '16 Workshop
- A sustainable practice method of hand-drawing by merging user's stroke and model's stroke MANPU '16 Workshop
- Closure-aware Sketch Simplification ACM Transactions on Graphics (SIGGRAPH Asia 2015 issue), Vol. 34, No. 6, November 2015, pp. 168:1-168:10.
- Towards the Automatic Anime Characters Creation with Generative Adversarial Networks Doujinshi in Comiket 92, summer 2017, with the booth number 05a, East-U, Third Day - Related to make.girls.moe
- A Study on Object Detection Method from Manga Images using CNN International Workshop on Advanced Image Technology 2018 (IWAIT 2018)
- Comics image processing: learning to segment text MANPU '16 Workshop
- Comic visualization on smartphones based on eye tracking MANPU '16 Workshop
- Designing a question-answering system for comic contents MANPU '16 Workshop
- Detection of comic books twin pages with a non-overlapping stitching method MANPU '16 Workshop
- Emotional arousal estimation while reading comics based on physiological signal analysis MANPU '16 Workshop
- Estimation of structure of four-scene comics by convolutional neural networks MANPU '16 Workshop
- Face Detection for Comic Images with Deformable Part Model The Fourth IIEEJ International Workshop on Image Electronics and Visual Computing
- Manga content analysis using physiological signals MANPU '16 Workshop
- Manga generator, a future of interactive manga media: invited talk paper MANPU '16 Workshop
- Manga109 dataset and creation of metadata MANPU '16 Workshop
- Line-Based Drawing Style Description for Manga Classification Proceedings of ACM International Conference on Multimedia. 781–784
- Object Detection for Comics using Manga109 Annotations Arxiv
- Retrieval of comic book images using context relevance information MANPU '16 Workshop
- Segmentation and indexation of complex objects in comic book images Université de La Rochelle
- Sketch-based manga retrieval using manga109 dataset Multimedia Tools and Applications October 2017, Volume 76, Issue 20, pp 21811–21838
- Text-aware balloon extraction from manga The Visual Computer: International Journal of Computer Graphics archive, Volume 32 Issue 4, April 2016, Pages 501-511 - Related to moeka.me/mangaEditor
- Toward speech text recognition for comic books MANPU '16 Workshop
- Stereoscopizing Cel Animations ACM Transactions on Graphics (SIGGRAPH Asia 2013 issue), Vol. 32, No. 6, November 2013, pp. 223:1-223:10.
- Using Posters to Recommend Anime and Mangas in a Cold-Start Scenario MANPU '17 Workshop
- For
Network Implementations
, use the following format:- [project-name](http://github-or-project-homepage.com) - Description
. - For
Papers
, use the following format:- [paper-title](http://paper-pdf-direct-link-(perferred)-or-library-page) *published-in-(optional)* - Description & project related (optional)
. Datasets
,Networks Implementations
andPapers
sorted by alphabetical.- Follow the original capitalization of the name of the project (no need to covert letter case).
- Item descriptions begin with a capital letter, and no need to end with a period.