AwesomeAnimeResearch

signal processing or machine learning related to anime or manga

Papers

Summary of published or preprint papers

Dataset

Paper	Conference	Links
The Amazing Mysteries of the Gutter: Drawing Inferences Between Panels in Comic Book Narratives	CVPR2017	Github
Creative Flow+ Dataset	CVPR2019	HP
Building a Manga Dataset ”Manga109” with Annotations for Multimedia Applications	IEEE MultiMedia,2020	HP
DanbooRegion: An Illustration Region Dataset	ECCV2020	Github
Unconstrained Text Detection in Manga: a New Dataset and Baseline	ECCVW2020	Github
Cartoon Face Recognition: A Benchmark Dataset	ACM MM2020	Github
DAF:RE: A CHALLENGING, CROWD-SOURCED, LARGE-SCALE, LONG-TAILED DATASET FOR ANIME CHARACTER RECOGNITION		Github
AnimeCeleb: Large-Scale Animation CelebHeads Dataset for Head Reenactment	ECCV2022	Github
A Challenging Benchmark of Anime Style Recognition	CVPRW2022
COO: Comic Onomatopoeia Dataset for Recognizing Arbitrary or Truncated Texts	ECCV2022	Github
AnimeRun: 2D Animation Visual Correspondence from Open Source 3D Movies		HP
Parsing-Conditioned Anime Translation: A New Dataset and Method	ACM TG2023	Github
Semi-supervised reference-based sketch extraction using a contrastive learning framework	ACM TG2023	Github
Manga109Dialog: A Large-scale Dialogue Dataset for Comics Speaker Detection		Github
Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes	CVPR2023	Github

Image Generation

Subcategory	Paper	Conference	Links
Generation	Towards the Automatic Anime Characters Creation with Generative Adversarial Networks	Comiket92	HP
	Full-body High-resolution Anime Generation with Progressive Structure-conditional Generative Adversarial Networks	ECCVW2018	HP
	Generate Novel Image Styles using Weighted Hybrid Generative Adversarial Nets	IJCNN2018
	Towards Diverse Anime Face Generation: Active Label Completion and Style Feature Network	EUROGRAPHICS2019
	An Adaptive Control Algorithm for Stable Training of Generative Adversarial Networks	IEEE Access2019
	Overcoming Long-term Catastrophic Forgetting through Adversarial Neural Pruning and Synaptic Consolidation
	Autoencoding Generative Adversarial Networks		Github
	Classification Representations Can be Reused for Downstream Generations
	GAN Memory with No Forgetting	NeurIPS2020	Github
	Generating Full-Body Standing Figures of Anime Characters and Its Style Transfer by GAN
	HistoGAN: Controlling Colors of GAN-Generated and Real Images via Color Histograms	CVPR2021	Github
	Efficient Continual Adaptation for Generative Adversarial Networks
	Generating "Ideal" Anime Opening Frames Using Neural Networks	ElConRus2021
	CoPE: Conditional image generation using Polynomial Expansions
	StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators	SIGGRAPH2022	Github
	DisUnknown: Distilling Unknown Factors for Disentanglement Learning	ICCV2021	Github
	Combating Mode Collapse in GANs via Manifold Entropy Estimation		Github
Few-shot	Image Generation From Small Datasets via Batch Statistics Adaptation	ICCV2019	Github
	FEW-SHOT ADAPTATION OF GENERATIVE ADVERSARIAL NETWORKS		Github
	MineGAN: effective knowledge transfer from GANs to target domains with few images	CVPR2020	Github
	Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANs	CVPRW2020	Github
	DATA INSTANCE PRIOR FOR TRANSFER LEARNING IN GANS
	MineGAN++: Mining Generative Models for Efficient Knowledge Transfer to Limited Data Domains
	Data InStance Prior (DISP) in Generative Adversarial Networks	WACV2022
	Controlling StyleGANs Using Rough Scribbles via One-shot Learning	CAVW2022	HP
Interpretability	RPGAN: GANs Interpretability via Random Routing		Github
	Unsupervised Discovery of Interpretable Directions in the GAN Latent Space	ICML2020	Github
	Closed-Form Factorization of Latent Semantics in GANs	CVPR2021	Github
	Unsupervised Discovery of Disentangled Manifolds in GANs
	Do Generative Models Know Disentanglement? Contrastive Learning is All You Need		Github
	Surrogate Gradient Field for Latent Space Manipulation	CVPR2021
	EigenGAN: Layer-Wise Eigen-Learning for GANs		Github
	Discovering Interpretable Latent Space Directions of GANs Beyond Binary Attributes	CVPR2021
	Discovering Density-Preserving Latent Space Walks in GANs for Semantic Image Transformations	MM 2021
	Self-supervised Enhancement of Latent Discovery in GANs	AAAI2022
	Unsupervised Discovery of Disentangled Interpretable Directions for Layer-Wise GAN	Big Data2022
Montage	MontageGAN: Generation and Assembly of Multiple Components by GANs	ICPR2022	Github
	Sprite-from-Sprite: Cartoon Animation Decomposition with Self-supervised Sprite Estimation	TOG2022
Text-to-Image	Adding Conditional Control to Text-to-Image Diffusion Models		Github
	DreamArtist: Towards Controllable One-Shot Text-to-Image Generation via Positive-Negative Prompt-Tuning		Github

Image-to-image Translation

Subcategory	Paper	Conference	Link
Face2anime	Improving Shape Deformation in Unsupervised Image-to-Image Translation	ECCV2018	Github
	Twin-GAN – Unpaired Cross-Domain Image Translation with Weight-Sharing GANs		Github
	DA-GAN: Instance-level Image Translation by Deep Attention Generative Adversarial Networks	CVPR2018	Github
	Landmark Assisted CycleGAN for Cartoon Face Generation
	Generating Anime from Real Human Image with Adversarial Training	ICASERT2019
	Auto-Encoding for Shared Cross Domain Feature Representation and Image-to-Image Translation
	Few-shot Knowledge Transfer for Fine-grained Cartoon Face Generation
	Unsupervised Image-to-Image Translation via Pre-trained StyleGAN2 Network		Github
	A Note on Data Biases in Generative Models	NeurIPSW2020
	Turn Real People into Anime Cartoonization	ICCECE2021
	AniGAN: Style-Guided Generative Adversarial Networks for Unsupervised Anime Face Generation		Github
	Multi-CartoonGAN for Conditional Artistic Face Translation	JSAI2021
	GANs N’ Roses: Stable, Controllable, Diverse Image to Image Translation (works for videos too!)		Github
	FINE-TUNING STYLEGAN2 FOR CARTOON FACE GENERATION		Github
	AgileGAN: Stylizing Portraits by Inversion-Consistent Transfer Learning	ACM Trans. Graph. 2021	Github
	A Domain Gap Aware Generative Adversarial Network for Multi-domain Image Translation
	[Cross-Domain Style Mixing for Face