Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
AwesomeAnimeResearch
Papers, repository and other data about anime or manga research. Please let me know if you have information that the list does not include.
https://github.com/SerialLain3170/AwesomeAnimeResearch
Last synced: 4 days ago
JSON representation
-
Papers
-
Image Generation
- Unsupervised Discovery of Disentangled Interpretable Directions for Layer-Wise GAN
- Towards Diverse Anime Face Generation: Active Label Completion and Style Feature Network
- Towards the Automatic Anime Characters Creation with Generative Adversarial Networks
- Full-body High-resolution Anime Generation with Progressive Structure-conditional Generative Adversarial Networks - generation/) |
- Towards Diverse Anime Face Generation: Active Label Completion and Style Feature Network
- Overcoming Long-term Catastrophic Forgetting through Adversarial Neural Pruning and Synaptic Consolidation
- Autoencoding Generative Adversarial Networks - keras) |
- 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
- DisUnknown: Distilling Unknown Factors for Disentanglement Learning
- Combating Mode Collapse in GANs via Manifold Entropy Estimation
- Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANs
- Controlling StyleGANs Using Rough Scribbles via One-shot Learning
- RPGAN: GANs Interpretability via Random Routing
- Unsupervised Discovery of Interpretable Directions in the GAN Latent Space
- Closed-Form Factorization of Latent Semantics in GANs
- Unsupervised Discovery of Disentangled Manifolds in GANs
- Surrogate Gradient Field for Latent Space Manipulation
- Unsupervised Discovery of Disentangled Interpretable Directions for Layer-Wise GAN
- Adding Conditional Control to Text-to-Image Diffusion Models
- DreamArtist: Towards Controllable One-Shot Text-to-Image Generation via Positive-Negative Prompt-Tuning - stable-diffusion) |
- Unsupervised Discovery of Disentangled Interpretable Directions for Layer-Wise GAN
- Unsupervised Discovery of Disentangled Interpretable Directions for Layer-Wise GAN
- Unsupervised Discovery of Disentangled Interpretable Directions for Layer-Wise GAN
- Unsupervised Discovery of Disentangled Interpretable Directions for Layer-Wise GAN
- Unsupervised Discovery of Disentangled Interpretable Directions for Layer-Wise GAN
- Unsupervised Discovery of Disentangled Interpretable Directions for Layer-Wise GAN
- Unsupervised Discovery of Disentangled Interpretable Directions for Layer-Wise GAN
- Unsupervised Discovery of Disentangled Interpretable Directions for Layer-Wise GAN
- Unsupervised Discovery of Disentangled Interpretable Directions for Layer-Wise GAN
- Unsupervised Discovery of Disentangled Interpretable Directions for Layer-Wise GAN
- Unsupervised Discovery of Disentangled Interpretable Directions for Layer-Wise GAN
- Unsupervised Discovery of Disentangled Interpretable Directions for Layer-Wise GAN
- Towards Diverse Anime Face Generation: Active Label Completion and Style Feature Network
- Unsupervised Discovery of Disentangled Interpretable Directions for Layer-Wise GAN
- Unsupervised Discovery of Disentangled Interpretable Directions for Layer-Wise GAN
- Unsupervised Discovery of Disentangled Interpretable Directions for Layer-Wise GAN
- Unsupervised Discovery of Disentangled Interpretable Directions for Layer-Wise GAN
- Unsupervised Discovery of Disentangled Interpretable Directions for Layer-Wise GAN
- Unsupervised Discovery of Disentangled Interpretable Directions for Layer-Wise GAN
- Unsupervised Discovery of Disentangled Interpretable Directions for Layer-Wise GAN
- Unsupervised Discovery of Disentangled Interpretable Directions for Layer-Wise GAN
- Unsupervised Discovery of Disentangled Interpretable Directions for Layer-Wise GAN
- Unsupervised Discovery of Disentangled Interpretable Directions for Layer-Wise GAN
- Unsupervised Discovery of Disentangled Interpretable Directions for Layer-Wise GAN
- Unsupervised Discovery of Disentangled Interpretable Directions for Layer-Wise GAN
- Unsupervised Discovery of Disentangled Interpretable Directions for Layer-Wise GAN
- Unsupervised Discovery of Disentangled Interpretable Directions for Layer-Wise GAN
- Unsupervised Discovery of Disentangled Interpretable Directions for Layer-Wise GAN
- Unsupervised Discovery of Disentangled Interpretable Directions for Layer-Wise GAN
- Unsupervised Discovery of Disentangled Interpretable Directions for Layer-Wise GAN
- Unsupervised Discovery of Disentangled Interpretable Directions for Layer-Wise GAN
- Unsupervised Discovery of Disentangled Interpretable Directions for Layer-Wise GAN
-
Dataset
- The Amazing Mysteries of the Gutter: Drawing Inferences Between Panels in Comic Book Narratives
- Unconstrained Text Detection in Manga: a New Dataset and Baseline - Text-Segmentation) |
- DAF:RE: A CHALLENGING, CROWD-SOURCED, LARGE-SCALE, LONG-TAILED DATASET FOR ANIME CHARACTER RECOGNITION
- AnimeCeleb: Large-Scale Animation CelebHeads Dataset for Head Reenactment
- COO: Comic Onomatopoeia Dataset for Recognizing Arbitrary or Truncated Texts - Comic-Onomatopoeia) |
- Building a Manga Dataset ”Manga109” with Annotations for Multimedia Applications
-
Image-to-image Translation
- Improving Shape Deformation in Unsupervised Image-to-Image Translation
- Landmark Assisted CycleGAN for Cartoon Face Generation
- Auto-Encoding for Shared Cross Domain Feature Representation and Image-to-Image Translation
- A Note on Data Biases in Generative Models
- FINE-TUNING STYLEGAN2 FOR CARTOON FACE GENERATION - jihye/Cartoon-StyleGAN) |
- Cross-Domain Style Mixing for Face Cartoonization
- U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation
- AttentionGAN: Unpaired Image-to-Image Translation using Attention-Guided Generative Adversarial Networks
- Unpaired Image-to-Image Translation using Adversarial Consistency Loss - lab/ACL-GAN) |
- Feature Quantization Improves GAN Training - GAN) |
- Interpolation based Anime Face Style Transfer
- SPatchGAN: A Statistical Feature Based Discriminator for Unsupervised Image-to-Image Translation
- Good Artists Copy, Great Artists Steal: Model Extraction Attacks Against Image Translation Generative Adversarial Networks
- Unaligned Image-to-Image Translation by Learning to Reweight
- UVCGAN: UNET VISION TRANSFORMER CYCLE-CONSISTENT GAN FOR UNPAIRED IMAGE-TO-IMAGE TRANSLATION
- Unpaired Cartoon Image Synthesis via Gated Cycle Mapping
- Unpaired Image-to-Image Translation using Negative Learning for Noisy Patches
- Hyprogan: Breaking the Dimensional wall From Human to Anime
- Alleviating Semantics Distortion in Unsupervised Low-Level Image-to-Image Translation via Structure Consistency Constraint
- Comixify: Transform video into a comics
- GANILLA: Generative adversarial networks for image to illustration translation
- CartoonRenderer: An Instance-based Multi-Style Cartoon Image Translator
- Learning to Cartoonize Using White-box Cartoon Representations - box-Cartoonization) |
- Generative Adversarial Networks for photo to Hayao Miyazaki style cartoons - gan) |
- AnimeGAN: a novel lightweight GAN for photo animation
- GAN-based Multi-Style Photo Cartoonization
- Pseudo-Supervised Learning for Semantic Multi-Style Transfer
- Cartoonize Images using TinyML Strategies with Transfer Learning
- Transfer photo to anime with dual discriminators GAN
- ARGAN: Fast Converging GAN for Animation Style Transfer
- Unsupervised Coherent Video Cartoonization with Perceptual Motion Consistency
- Learning to Incorporate Texture Saliency Adaptive Attention to Image Cartoonization
- Scenimefy: Learning to Craft Anime Scene via Semi-Supervised Image-to-Image Translation - J/Scenimefy) |
- SmartPaint: a co-creative drawing system based on generative adversarial networks
- PI-REC: Progressive Image Reconstruction Network With Edge and Color Domain - REC) |
- Modeling Artistic Workflows for Image Generation and Editing
- Deep Sketch-guided Cartoon Video Inbetweening
- SketchBetween: Video-to-Video Synthesis for Sprite Animation via Sketches
- How to train your conditional GAN: An approach using geometrically structured latent manifolds
- PMSGAN: Parallel Multistage GANs for Face Image Translation
- AniFaceDrawing: Anime Portrait Exploration during Your Sketching
- MangaGAN: Unpaired Photo-to-Manga Translation Based on The Methodology of Manga Drawing
- Anime-to-Real Clothing: Cosplay Costume Generation via Image-to-Image Translation
- Anime Style Space Exploration Using Metric Learning and Generative Adversarial Networks
- Disentangling Style and Content in Anime Illustrations - disentangle) |
- RAG: Facial Attribute Editing by Learning Residual Attributes
- StarGAN Based Facial Expression Transfer for Anime Characters
- Few-shot Semantic Image Synthesis Using StyleGAN Prior - yuki-t/Fewshot-SMIS) |
- Fine-Grained Control of Artistic Styles in Image Generation
- JoJoGAN: One Shot Face Stylization
- Unsupersived Image Texture Transfer Based On Generative Adversarial Network
- Styleverse: Towards Identity Stylization across Heterogeneous Domains
- Mind the Gap: Domain Gap Control for Single Shot Domain Adaptation for Generative Adversarial Networks
- Pastiche Master: Exemplar-Based High-Resolution Portrait Style Transfer
- Towards Diverse and Faithful One-shot Adaption of Generative Adversarial Networks
- LANIT: Language-Driven Image-to-Image Translation for Unlabeled Data - CVLAB/LANIT) |
- HRInversion: High-Resolution GAN Inversion for Cross-Domain Image Synthesis
- Translation of Illustration Artist Style Using Sailormoonredraw Data
- Twin-GAN – Unpaired Cross-Domain Image Translation with Weight-Sharing GANs
- Breaking the cycle—Colleagues are all you need - GAN) |
- Unpaired Image-to-Image Translation using Adversarial Consistency Loss - lab/ACL-GAN) |
- Deep Sketch-guided Cartoon Video Inbetweening
- Unaligned Image-to-Image Translation by Learning to Reweight
- CartoonRenderer: An Instance-based Multi-Style Cartoon Image Translator
- Good Artists Copy, Great Artists Steal: Model Extraction Attacks Against Image Translation Generative Adversarial Networks
- Interactive Cartoonization with Controllable Perceptual Factors
- A Novel Double-Tail Generative Adversarial Network for Fast Photo Animation
- Diffutoon: High-Resolution Editable Toon Shading via Diffusion Models - cilab.github.io/DiffutoonProjectPage/) |
- U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation
- How to train your conditional GAN: An approach using geometrically structured latent manifolds
- Anime Style Space Exploration Using Metric Learning and Generative Adversarial Networks
- Breaking the cycle—Colleagues are all you need - GAN) |
- SPatchGAN: A Statistical Feature Based Discriminator for Unsupervised Image-to-Image Translation
- GANILLA: Generative adversarial networks for image to illustration translation
- Generative Adversarial Networks for photo to Hayao Miyazaki style cartoons - gan) |
- PI-REC: Progressive Image Reconstruction Network With Edge and Color Domain - REC) |
- Modeling Artistic Workflows for Image Generation and Editing
- SketchBetween: Video-to-Video Synthesis for Sprite Animation via Sketches
- Anime-to-Real Clothing: Cosplay Costume Generation via Image-to-Image Translation
- JoJoGAN: One Shot Face Stylization
- LANIT: Language-Driven Image-to-Image Translation for Unlabeled Data - CVLAB/LANIT) |
-
Automatic Line Art Colorization
- Automatic Sketch Colorization with Tandem Conditional Adversarial Networks
- Do You Like Sclera? Sclera-region Detection and Colorization for Anime Character Line Drawings
- Colorization for Anime Sketches with Cycle-Consistent Adversarial Network
- Seg2pix: Few Shot Training Line Art Colorization with Segmented Image Data
- Semi-automatic Manga Colorization Using Conditional Adversarial Networks - colorization) |
- Stylized-Colorization for Line Arts
- Generative Probabilistic Image Colorization
- TexToons: Practical Texture Mapping for Hand-drawn Cartoon Animations
- Outline Colorization through Tandem Adversarial Networks
- A Fast and Efficient Semi-guided Algorithm for Flat Coloring Line-arts
- Auto-painter: Cartoon Image Generation from Sketch by Using Conditional Wasserstein Generative Adversarial Networks
- User-Guided Deep Anime Line Art Colorization with Conditional Adversarial Networks
- Two-stage Sketch Colorization
- Anime Sketch Coloring with Swish-gated Residual U-net and Spectrally Normalized GAN - Sketch-Coloring-with-Swish-Gated-Residual-UNet) |
- Interactive Anime Sketch Colorization with Style Consistency via a Deep Residual Neural Network
- Semi-Auto Sketch Colorization Based on Conditional Generative Adversarial Networks - BMEI2019 | |
- MANGAN: ASSISTING COLORIZATION OF MANGA CHARACTERS CONCEPT ART USING CONDITIONAL GAN
- Two-Stage Sketch Colorization With Color Parsing
- Cartoon image colorization based on emotion recognition and superpixel color resolution
- Automatic Colorization of Anime Style Illustrations Using a Two-Stage Generator
- Line Art Colorization with Concatenated Spatial Attention
- User-Guided Line Art Flat Filling with Split Filling Mechanism
- Deep Edge-Aware Interactive Colorization against Color-Bleeding Effects
- Dual Color Space Guided Sketch Colorization
- Late-resizing: A Simple but Effective Sketch Extraction Strategy for Improving Generalization of Line-art Colorization
- Guiding Users to Where to Give Color Hints for Efficient Interactive Sketch Colorization via Unsupervised Region Prioritization
- Diffusart: Enhancing Line Art Colorization with Conditional Diffusion Models
- Unsupervised Colorization of Black-and-White Cartoons
- Reference-based Manga Colorization by Graph Correspondence Using Quadratic Programming
- Deep Manga Colorization with Color Style Extraction by Conditional Adversarially Learned Inference
- Style Transfer for Anime Sketches with Enhanced Residual U-net and Auxiliary Classifier GAN
- cGAN-based Manga Colorization Using a Single Training Image
- Comicolorization: Semi-Automatic Manga Colorization
- Automatic manga colorization with color style by generative adversarial nets
- Attentioned Deep Paint
- Semantic Example Guided Image-to-Image Translation
- Graph Matching based Anime Colorization with Multiple References
- Reference-Based Sketch Image Colorization using Augmented-Self Reference and Dense Semantic Correspondence
- Multi-Density Sketch-to-Image Translation Network
- Deep-Eyes: Fully Automatic Anime Character Colorization with Painting of Details on Empty Pupils
- Colorization of Line Drawings with Empty Pupils
- Anime Sketch Colorization by Component-based Matching using Deep Appearance Features and Graph Representation
- Anime Style Transfer With Spatially-Adaptive Normalization
- Exploring Sketch-based Character Design Guided by Automatic Colorization
- PAINTING STYLE-AWARE MANGA COLORIZATION BASED ON GENERATIVE ADVERSARIAL NETWORKS
- Disentangled and controllable sketch creation based ondisentangling the structure and color enhancement
- Reference-guided structure-aware deep sketch colorization for cartoons
- Exemplar-Based Sketch Colorization with Cross-Domain Dense Semantic Correspondence
- Eliminating Gradient Conflict in Reference-based Line-Art Colorization
- Improving Reference-Based Image Colorization For Line Arts Via Feature Aggregation And Contrastive Learning
- Semi-Automatic Colorization Pipeline for Anime Characters and its Evaluation in Production
- ATTENTION-AWARE ANIME LINE DRAWING COLORIZATION
- AnimeDiffusion: Anime Face Line Drawing Colorization via Diffusion Models
- Two-Step Training: Adjustable Sketch Colourization via Reference Image and Text Tag - tellurion/sketch_colorizer) |
- Tag2Pix: Line Art Colorization Using Text Tag With SECat and Changing Loss
- Line Art Colorization Based on Explicit Region Segmentation
- Automatic Temporally Coherent Video Colorization - Thasarathan/TCVC) |
- Artist-Guided Semiautomatic Animation Colorization
- Deep Line Art Video Colorization with a Few References
- Line Art Correlation Matching Feature Transfer Network for Automatic Animation Colorization
- The Animation Transformer: Visual Correspondence via Segment Matching
- Coloring anime line art videos with transformation region enhancement network
- Reference-guided structure-aware deep sketch colorization for cartoons
- Reference-guided structure-aware deep sketch colorization for cartoons
- Reference-guided structure-aware deep sketch colorization for cartoons
- Reference-guided structure-aware deep sketch colorization for cartoons
- Reference-guided structure-aware deep sketch colorization for cartoons
- Reference-guided structure-aware deep sketch colorization for cartoons
- ColorizeDiffusion: Adjustable Sketch Colorization with Reference Image and Text
- Reference-guided structure-aware deep sketch colorization for cartoons
- ColorizeDiffusion: Adjustable Sketch Colorization with Reference Image and Text
- Reference-guided structure-aware deep sketch colorization for cartoons
- Reference-guided structure-aware deep sketch colorization for cartoons
- Reference-guided structure-aware deep sketch colorization for cartoons
- Multi-Density Sketch-to-Image Translation Network
- Reference-guided structure-aware deep sketch colorization for cartoons
- Reference-guided structure-aware deep sketch colorization for cartoons
- Reference-guided structure-aware deep sketch colorization for cartoons
- Robust Manga Page Colorization via Coloring Latent Space
- Learning Inclusion Matching for Animation Paint Bucket Coloriation
- Reference-guided structure-aware deep sketch colorization for cartoons
- cGAN-based Manga Colorization Using a Single Training Image
- Reference-guided structure-aware deep sketch colorization for cartoons
- Outline Colorization through Tandem Adversarial Networks
- Deep Edge-Aware Interactive Colorization against Color-Bleeding Effects
- Guiding Users to Where to Give Color Hints for Efficient Interactive Sketch Colorization via Unsupervised Region Prioritization
- Style Transfer for Anime Sketches with Enhanced Residual U-net and Auxiliary Classifier GAN
- Semantic Example Guided Image-to-Image Translation
- Reference-Based Sketch Image Colorization using Augmented-Self Reference and Dense Semantic Correspondence
- PAINTING STYLE-AWARE MANGA COLORIZATION BASED ON GENERATIVE ADVERSARIAL NETWORKS
- Reference-guided structure-aware deep sketch colorization for cartoons
- Eliminating Gradient Conflict in Reference-based Line-Art Colorization
- ATTENTION-AWARE ANIME LINE DRAWING COLORIZATION
- AnimeDiffusion: Anime Face Line Drawing Colorization via Diffusion Models
- Automatic Temporally Coherent Video Colorization - Thasarathan/TCVC) |
-
Automatic Character Lighting
- Ink-and-Ray: Bas-Relief Meshes for Adding Global Illumination Effects to Hand-Drawn Characters
- Deep Normal Estimation for Automatic Shading of Hand-Drawn Characters - Sense/DeepNormals) |
- Automatic Illumination Effects for 2D Characters
- Generating Digital Painting Lighting Effects via RGB-space Geometry
- Learning to Shadow Hand-drawn Sketches
- SmartShadow: Artistic Shadow Drawing Tool for Line Drawings
- Automatic Illumination of Flat-Colored Drawings by 3D Augmentation of 2D Silhouettes
- Learning to Shadow Hand-drawn Sketches
-
Automatic Illustration Editing
- Decomposing Images into Layers with Advanced Color Blending - koyama/unblending) |
- Spatially Controllable Image Synthesis with Internal Representation Collaging - collage) |
- Erasing Appearance Preservation in Optimization-based Smoothing
- Cross-Domain and Disentangled Face Manipulation with 3D Guidance
- L2M-GAN: Learning to Manipulate Latent Space Semantics for Facial Attribute Editing
- Deep Unfolding with Normalizing Flow Priors for Inverse Problems
- Sketch-based Anime Hairstyle Editing with Generative Inpainting
- DyStyle: Dynamic Neural Network for Multi-Attribute-Conditioned Style Editing
- Improving The Quality Of Illustrations: Transforming Amateur Illustrations To A Professional Standard
- Universal Face Restoration With Memorized Modulation
- Unsupervised Learning of Compositional Energy Concepts
- Reference-based Image Composition with Sketch via Structure-aware Diffusion Model - by-Sketch) |
- Instance-guided Cartoon Editing with a Large-scale Dataset
- Re:Draw - Context Aware Translation as a Controllable Method for Artistic Production
- DreamTuner: Single Image is Enough for Subject-Driven Generation
- Deep Unfolding with Normalizing Flow Priors for Inverse Problems
- Unsupervised Learning of Compositional Energy Concepts
- Reference-based Image Composition with Sketch via Structure-aware Diffusion Model - by-Sketch) |
-
Automatic Sketch Editing
- Learning to Simplify: Fully Convolutional Networks for Rough Sketch Cleanup
- Mastering Sketching: Adversarial Augmentation for Structured Prediction
- Perceptual-aware Sketch Simplification Based on Integrated VGG Layers
- Progressive Full Data Convolutional Neural Networks for Line Extraction from Anime-Style Illustrations
- One-shot Line Extraction from Color Illustrations
- A Drawing Support System for Sketching Aging Anime Faces
- Real-Time Data-Driven Interactive Rough Sketch Inking
- End-to-End Line Drawing Vectorization
- Mastering Sketching: Adversarial Augmentation for Structured Prediction
-
Automatic Animation Inbetweening
- A filter based approach for inbetweening (Japanese)
- DiLight: Digital light table – Inbetweening for 2D animations using guidelines
- Optical Flow Based Line Drawing Frame Interpolation Using Distance Transform to Support Inbetweenings
- Deep Animation Video Interpolation in the Wild
- Improving the Perceptual Quality of 2D Animation Interpolation - anime-interpolator/) |
- Enhanced Deep Animation Video Interpolation
- Deep Geometrized Cartoon Line Inbetweening
- Automatic Animation Inbetweening
- Automatic Animation Inbetweening
- Automatic Animation Inbetweening
- Automatic Animation Inbetweening
- Automatic Animation Inbetweening
- Deep Animation Video Interpolation in the Wild
- Automatic Animation Inbetweening
- A filter based approach for inbetweening (Japanese)
- Enhanced Deep Animation Video Interpolation
- Automatic Animation Inbetweening
-
Automatic Image Enhancement
- Enhancement of Anime Imaging Enlargement using Modified Super-Resolution CNN - anime) |
- Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data - ESRGAN) |
- A Transformer-Based Model for Super-Resolution of Anime Image
- AnimeSR: Learning Real-World Super-Resolution Models for Animation Videos
- APISR: Anime Production Inspired Real-World Anime Super-Resolution
- Enhancement of Anime Imaging Enlargement using Modified Super-Resolution CNN - anime) |
- Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data - ESRGAN) |
- AnimeSR: Learning Real-World Super-Resolution Models for Animation Videos
- APISR: Anime Production Inspired Real-World Anime Super-Resolution
-
Character Animating
- MakeItTalk: Speaker-Aware Talking-Head Animation
- CPTNet: Cascade Pose Transform Network for Single Image Talking Head Animation
- Collaborative Neural Rendering using Anime Character Sheets - research/CONR) |
- Language-Guided Face Animation by Recurrent StyleGAN-based Generator - guided-animation) |
- Hierarchical Feature Warping and Blending for Talking Head Animation
- AnimateDiff-Lightning: Cross-Model Diffusion Distillation - Lightning) |
- Collaborative Neural Rendering using Anime Character Sheets - research/CONR) |
- Language-Guided Face Animation by Recurrent StyleGAN-based Generator - guided-animation) |
-
Manga Application
- Synthesis of Screentone Patterns of Manga Characters
- Generating Manga from Illustrations via Mimicking Manga Workflow
- Hair Shading Style Transfer for Manga with cGAN
- Exploiting Aliasing for Manga Restoration
- Seamless Manga Inpainting with Semantics Awareness
- Method for Real Time Text Extraction of Digital Manga Comic
- Facial Landmark Detection for Manga Images
- Extraction of Frame Sequences in the Manga Context
- Towards Content-Aware Pixel-Wise Comic Panel Segmentation
- Towards Fully Automated Manga Translation
- Estimating Image Depth in the Comics Domain
- Vectorization of Raster Manga by Deep Reinforcement Learning
- Unsupervised Manga Character Re-identification via Face-body and Spatial-temporal Associated Clustering
- Towards Content-Aware Pixel-Wise Comic Panel Segmentation
- Towards Content-Aware Pixel-Wise Comic Panel Segmentation
- Towards Content-Aware Pixel-Wise Comic Panel Segmentation
- Towards Content-Aware Pixel-Wise Comic Panel Segmentation
- Towards Content-Aware Pixel-Wise Comic Panel Segmentation
- Panel-Page-Aware Comic Genre Understanding
- Manga Rescreening with Interpretable Screentone Representation
- Towards Content-Aware Pixel-Wise Comic Panel Segmentation
- Towards Content-Aware Pixel-Wise Comic Panel Segmentation
- Towards Content-Aware Pixel-Wise Comic Panel Segmentation
- Towards Content-Aware Pixel-Wise Comic Panel Segmentation
- Towards Content-Aware Pixel-Wise Comic Panel Segmentation
- Towards Content-Aware Pixel-Wise Comic Panel Segmentation
- SKETCH2MANGA: SHADED MANGA SCREENING FROM SKETCH WITH DIFFUSION MODELS
- Towards Content-Aware Pixel-Wise Comic Panel Segmentation
- Zero-Shot Character Identification and Speaker Prediction in Comics via Iterative Multimodal Fusion
- Towards Content-Aware Pixel-Wise Comic Panel Segmentation
- Towards Content-Aware Pixel-Wise Comic Panel Segmentation
- Towards Content-Aware Pixel-Wise Comic Panel Segmentation
- Towards Fully Automated Manga Translation
- Facial Landmark Detection for Manga Images
- Towards Content-Aware Pixel-Wise Comic Panel Segmentation
- Unsupervised Manga Character Re-identification via Face-body and Spatial-temporal Associated Clustering
-
Representation Learning
-
Pose Estimation
- Pose Estimation of Anime/Manga Characters: A Case for Synthetic Data
- Transfer Learning for Pose Estimation of Illustrated Characters - pose-estimator) |
- VLPose: Bridging the Domain Gap in Pose Estimation with Language-Vision Tuning
- Transfer Learning for Pose Estimation of Illustrated Characters - pose-estimator) |
-
Image Retrieval
-
Visual Correspondence
-
Character Recognition
- Object Detection for Comics using Manga109 Annotations
- Graph Jigsaw Learning for Cartoon Face Recognition
- ACFD: Asymmetric Cartoon Face Detector
- CAST: CHARACTER LABELING IN ANIMATION USING SELF-SUPERVISION BY TRACKING
- Open-Vocabulary DETR with Conditional Matching - DETR) |
- AniWho : A Quick and Accurate Way to Classify Anime Character Faces in Images
- GCN-Based Multi-Modal Multi-Label Attribute Classification in Anime Illustration Using Domain-Specific Semantic Features
- Hierarchical Multi-Label Attribute Classification With Graph Convolutional Networks on Anime Illustration
- CNN based Extraction of Panels/Characters from Bengali Comic Book Page Images
- Deep Learning-Based Classification of the Polar Emotions of “Moe”-Style Cartoon Pictures
- Open-Vocabulary DETR with Conditional Matching - DETR) |
-
3D Character Creation
- Automatic Generation of 3D Natural Anime-like Non-Player Characters with Machine Learning
- DreamWaltz: Make a Scene with Complex 3D Animatable Avatars - Research/DreamWaltz) |
- DreamWaltz: Make a Scene with Complex 3D Animatable Avatars - Research/DreamWaltz) |
-
Robotics
-
Adult Content Detection
- KidsGUARD: Fine Grained Approach for Child Unsafe Video Representation and Detection - iiitd/kidsguard-sac) |
- An Evaluation of Traditional and CNN-Based Feature Descriptors for Cartoon Pornography Detection
- A Deep Learning-Based Approach for Inappropriate Content Detection and Classification of YouTube Videos
-
Survey & Review
- A Survey of Comics Research in Computer Science
- Computational Approaches to Comics Analysis
- Image Colorization: A Survey and Dataset
- Cartoon Image Processing: A Survey
- Anime like Character Face Generation: A survey
- Cartoon Image Processing: A Survey
- Cartoon Image Processing: A Survey
- Cartoon Image Processing: A Survey
- Cartoon Image Processing: A Survey
- Cartoon Image Processing: A Survey
- Cartoon Image Processing: A Survey
- Cartoon Image Processing: A Survey
- Cartoon Image Processing: A Survey
- Cartoon Image Processing: A Survey
- Cartoon Image Processing: A Survey
- Cartoon Image Processing: A Survey
- Cartoon Image Processing: A Survey
- Cartoon Image Processing: A Survey
- Cartoon Image Processing: A Survey
- Image Colorization: A Survey and Dataset
- Cartoon Image Processing: A Survey
- A Survey of Comics Research in Computer Science
- Cartoon Image Processing: A Survey
-
-
📂 Datasets
- Creative Flow+ Dataset
- DanbooRegion: An Illustration Region Dataset
- Cartoon Face Recognition: A Benchmark Dataset - PersonAI/iCartoonFace) |
- A Challenging Benchmark of Anime Style Recognition
- AnimeRun: 2D Animation Visual Correspondence from Open Source 3D Movies
- Manga109Dialog: A Large-scale Dialogue Dataset for Comics Speaker Detection - annotations) |
- Semi-supervised reference-based sketch extraction using a contrastive learning framework
- Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes - Research/HumanArt) |
- Parsing-Conditioned Anime Translation: A New Dataset and Method
- Building a Manga Dataset ”Manga109” with Annotations for Multimedia Applications
- Tails Tell Tales: Chapter-Wide Manga Transcriptions with Character Names
- CoMix: A Comprehensive Benchmark for Multi-Task Comic Understanding - dataset) |
- The Amazing Mysteries of the Gutter: Drawing Inferences Between Panels in Comic Book Narratives
- Unconstrained Text Detection in Manga: a New Dataset and Baseline - Text-Segmentation) |
- DAF:RE: A CHALLENGING, CROWD-SOURCED, LARGE-SCALE, LONG-TAILED DATASET FOR ANIME CHARACTER RECOGNITION
- COO: Comic Onomatopoeia Dataset for Recognizing Arbitrary or Truncated Texts - Comic-Onomatopoeia) |
-
📜 Papers
-
Image Generation
- Generate Novel Image Styles using Weighted Hybrid Generative Adversarial Nets
- An Adaptive Control Algorithm for Stable Training of Generative Adversarial Networks
- Classification Representations Can be Reused for Downstream Generations
- GAN Memory with No Forgetting
- Efficient Continual Adaptation for Generative Adversarial Networks
- Generating "Ideal" Anime Opening Frames Using Neural Networks
- CoPE: Conditional image generation using Polynomial Expansions
- StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators - nada) |
- FEW-SHOT ADAPTATION OF GENERATIVE ADVERSARIAL NETWORKS - 271/few-shot-gan) |
- MineGAN: effective knowledge transfer from GANs to target domains with few images
- 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
- Do Generative Models Know Disentanglement? Contrastive Learning is All You Need
- EigenGAN: Layer-Wise Eigen-Learning for GANs - Tensorflow) |
- Discovering Interpretable Latent Space Directions of GANs Beyond Binary Attributes
- Self-supervised Enhancement of Latent Discovery in GANs
- MontageGAN: Generation and Assembly of Multiple Components by GANs - montage-gan)|
- GAN Memory with No Forgetting
- Unsupervised Discovery of Disentangled Interpretable Directions for Layer-Wise GAN
- Generating Full-Body Standing Figures of Anime Characters and Its Style Transfer by GAN
- Controlling StyleGANs Using Rough Scribbles via One-shot Learning
- Sprite-from-Sprite: Cartoon Animation Decomposition with Self-supervised Sprite Estimation
- Unsupervised Discovery of Disentangled Interpretable Directions for Layer-Wise GAN
- Adding Conditional Control to Text-to-Image Diffusion Models
- HistoGAN: Controlling Colors of GAN-Generated and Real Images via Color Histograms
- RPGAN: GANs Interpretability via Random Routing
- Unsupervised Discovery of Disentangled Manifolds in GANs
- DreamArtist: Towards Controllable One-Shot Text-to-Image Generation via Positive-Negative Prompt-Tuning - stable-diffusion) |
- Unsupervised Discovery of Disentangled Interpretable Directions for Layer-Wise GAN
- Image Generation From Small Datasets via Batch Statistics Adaptation - atsu/small-dataset-image-generation) |
- Unsupervised Discovery of Disentangled Interpretable Directions for Layer-Wise GAN
- Towards Diverse Anime Face Generation: Active Label Completion and Style Feature Network
- Unsupervised Discovery of Disentangled Interpretable Directions for Layer-Wise GAN
- Towards the Automatic Anime Characters Creation with Generative Adversarial Networks
- DisUnknown: Distilling Unknown Factors for Disentanglement Learning
- Surrogate Gradient Field for Latent Space Manipulation
- Full-body High-resolution Anime Generation with Progressive Structure-conditional Generative Adversarial Networks - generation/) |
- Overcoming Long-term Catastrophic Forgetting through Adversarial Neural Pruning and Synaptic Consolidation
- Autoencoding Generative Adversarial Networks - keras) |
- Combating Mode Collapse in GANs via Manifold Entropy Estimation
- Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANs
- Unsupervised Discovery of Interpretable Directions in the GAN Latent Space
- Closed-Form Factorization of Latent Semantics in GANs
-
Image 2 Image Translation
- DA-GAN: Instance-level Image Translation by Deep Attention Generative Adversarial Networks - Lin/A-DA-GAN-architecture) |
- Generating Anime from Real Human Image with Adversarial Training
- Few-shot Knowledge Transfer for Fine-grained Cartoon Face Generation
- Unsupervised Image-to-Image Translation via Pre-trained StyleGAN2 Network
- Turn Real People into Anime Cartoonization
- AniGAN: Style-Guided Generative Adversarial Networks for Unsupervised Anime Face Generation - li-ai/AniGAN) |
- A Domain Gap Aware Generative Adversarial Network for Multi-domain Image Translation
- Neural Optimal Transport
- StyO: Stylize Your Face in Only One-Shot
- Multi-CartoonGAN for Conditional Artistic Face Translation
- GANs N’ Roses: Stable, Controllable, Diverse Image to Image Translation (works for videos too!)
- Appearance-preserved Portrait-to-anime Translation via Proxy-guided Domain Adaptation
- Twin-GAN – Unpaired Cross-Domain Image Translation with Weight-Sharing GANs
- Landmark Assisted CycleGAN for Cartoon Face Generation
- A Note on Data Biases in Generative Models
- Cross-Domain Style Mixing for Face Cartoonization
- Auto-Encoding for Shared Cross Domain Feature Representation and Image-to-Image Translation
-
-
Projects
-
Dataset
-
Image Generation
-
Image-to-Image Tranlation
-
Automatic Line Art Colorization
-
Super Resolution
-
Categories
Sub Categories
Image Generation
99
Automatic Line Art Colorization
97
Image-to-image Translation
81
Manga Application
36
Survey & Review
23
Automatic Illustration Editing
18
Image 2 Image Translation
17
Automatic Animation Inbetweening
17
Character Recognition
11
Automatic Image Enhancement
9
Dataset
9
Automatic Sketch Editing
9
Character Animating
8
Automatic Character Lighting
8
Pose Estimation
4
Adult Content Detection
3
3D Character Creation
3
Image Retrieval
3
Visual Correspondence
2
Image-to-Image Tranlation
2
Robotics
2
Representation Learning
1
Super Resolution
1