Sketch-based Manga Retrieval using Manga109 Dataset

Abstract

Manga (Japanese comics) are popular worldwide. However, current e-manga archives offer very limited search support, including keyword-based search by title or author, or tag-based categorization. To make the manga search experience more intuitive, efficient, and enjoyable, we propose a content-based manga retrieval system. First, we propose a manga-specific image-describing framework. It consists of efficient margin labeling, edge orientation histogram feature description, and approximate nearest-neighbor search using product quantization. Second, we propose a sketch-based interface as a natural way to interact with manga content. The interface provides sketch-based querying, relevance feedback, and query retouch. For evaluation, we built a novel dataset of manga images, Manga109, which consists of 109 comic books of 21,142 pages drawn by professional manga artists. To the best of our knowledge, Manga109 is currently the biggest dataset of manga images available for research. We conducted a comparative study, a localization evaluation, and a large-scale qualitative study. From the experiments, we verified that: (1) the retrieval accuracy of the proposed method is higher than those of previous methods; (2) the proposed method can localize an object instance with reasonable runtime and accuracy; and (3) sketch querying is useful for manga search.

13 pages

Cited by in corpus (99)

• Lightweight Image Super-Resolution with Information Multi-distillation Network
• Fast Parallel Hypertree Decompositions in Logarithmic Recursion Depth
• Image Super-Resolution Using Very Deep Residual Channel Attention Networks
• Residual Dense Network for Image Super-Resolution
• Unfolding the Alternating Optimization for Blind Super Resolution
• Blind Universal Bayesian Image Denoising with Gaussian Noise Level Learning
• Deep Learning for Multiple-Image Super-Resolution
• Diffusion Models, Image Super-Resolution And Everything: A Survey
• Building a Manga Dataset "Manga109" with Annotations for Multimedia Applications
• Single Image Super-Resolution via a Holistic Attention Network
• Lightweight Image Super-Resolution with Adaptive Weighted Learning Network
• SwinIR: Image Restoration Using Swin Transformer
• Cross-SRN: Structure-Preserving Super-Resolution Network with Cross Convolution
• HIPA: Hierarchical Patch Transformer for Single Image Super Resolution
• A Practical Contrastive Learning Framework for Single-Image Super-Resolution
• Hybrid Residual Attention Network for Single Image Super Resolution
• Large Kernel Distillation Network for Efficient Single Image Super-Resolution
• Attention in Attention Network for Image Super-Resolution
• Hitchhiker's Guide to Super-Resolution: Introduction and Recent Advances
• Residual Dense Network for Image Restoration
• Lightweight Feature Fusion Network for Single Image Super-Resolution
• Accurate and Lightweight Image Super-Resolution with Model-Guided Deep Unfolding Network
• Transforming Image Super-Resolution: A ConvFormer-based Efficient Approach
• Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Model
• Feedback Network for Image Super-Resolution
• Learning Texture Transformer Network for Image Super-Resolution
• Efficient Image Super-Resolution Using Pixel Attention
• Object Detection for Comics using Manga109 Annotations
• Image Super-Resolution with Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining
• DDistill-SR: Reparameterized Dynamic Distillation Network for Lightweight Image Super-Resolution
• UltraSR: Spatial Encoding is a Missing Key for Implicit Image Function-based Arbitrary-Scale Super-Resolution
• End-to-end Alternating Optimization for Real-World Blind Super Resolution
• Iterative Network for Image Super-Resolution
• Residual Feature Distillation Network for Lightweight Image Super-Resolution
• Closed-loop Matters: Dual Regression Networks for Single Image Super-Resolution
• End-to-end Alternating Optimization for Blind Super Resolution
• Gated Multiple Feedback Network for Image Super-Resolution
• Deep Back-Projection Networks For Super-Resolution
• Bridging Component Learning with Degradation Modelling for Blind Image Super-Resolution
• Blind Super-Resolution With Iterative Kernel Correction
• MAMNet: Multi-path Adaptive Modulation Network for Image Super-Resolution
• MAT: Multi-Range Attention Transformer for Efficient Image Super-Resolution
• Channel-wise and Spatial Feature Modulation Network for Single Image Super-Resolution
• Toward DNN of LUTs: Learning Efficient Image Restoration with Multiple Look-Up Tables
• Comicolorization: Semi-Automatic Manga Colorization
• Exploring Sparsity in Image Super-Resolution for Efficient Inference
• Lightweight Single-Image Super-Resolution Network with Attentive Auxiliary Feature Learning
• Fast and Robust Cascade Model for Multiple Degradation Single Image Super-Resolution
• Zero-shot sketch-based remote sensing image retrieval based on multi-level and attention-guided tokenization
• Improving Super-Resolution Performance using Meta-Attention Layers
• HASN: Hybrid Attention Separable Network for Efficient Image Super-resolution
• Progressive Perception-Oriented Network for Single Image Super-Resolution
• Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution
• Multi-grained Attention Networks for Single Image Super-Resolution
• MDCN: Multi-scale Dense Cross Network for Image Super-Resolution
• Scene Text Image Super-Resolution in the Wild
• Learning A Single Network for Scale-Arbitrary Super-Resolution
• AdaDM: Enabling Normalization for Image Super-Resolution
• DAF:re: A Challenging, Crowd-Sourced, Large-Scale, Long-Tailed Dataset For Anime Character Recognition
• KOALAnet: Blind Super-Resolution using Kernel-Oriented Adaptive Local Adjustment
• An Effective Single-Image Super-Resolution Model Using Squeeze-and-Excitation Networks
• MAANet: Multi-view Aware Attention Networks for Image Super-Resolution
• FreqNet: A Frequency-domain Image Super-Resolution Network with Dicrete Cosine Transform
• Robust Reference-based Super-Resolution via C2-Matching
• Fully Convolutional Pixel Adaptive Image Denoiser
• Pyramidal Dense Attention Networks for Lightweight Image Super-Resolution
• First-order State Space Model for Lightweight Image Super-resolution
• Fine-grained Attention and Feature-sharing Generative Adversarial Networks for Single Image Super-Resolution
• Image Formation Model Guided Deep Image Super-Resolution
• FCSR-GAN: Joint Face Completion and Super-resolution via Multi-task Learning
• Visual representation of negation: Real world data analysis on comic image design
• Deep Interleaved Network for Image Super-Resolution With Asymmetric Co-Attention
• Scale-Aware Dynamic Network for Continuous-Scale Super-Resolution
• Blind Image Super-resolution with Elaborate Degradation Modeling on Noise and Kernel
• Towards Fully Automated Manga Translation
• Boosting High-Level Vision with Joint Compression Artifacts Reduction and Super-Resolution
• Learning Deep Interleaved Networks with Asymmetric Co-Attention for Image Restoration
• W2S: Microscopy Data with Joint Denoising and Super-Resolution for Widefield to SIM Mapping
• Exploring Linear Attention Alternative for Single Image Super-Resolution
• CRNet: Image Super-Resolution Using A Convolutional Sparse Coding Inspired Network
• FC${}^2$N: Fully Channel-Concatenated Network for Single Image Super-Resolution
• Single-Image Super-Resolution Reconstruction based on the Differences of Neighboring Pixels
• ASDN: A Deep Convolutional Network for Arbitrary Scale Image Super-Resolution
• Feedback Pyramid Attention Networks for Single Image Super-Resolution
• UNet--: Memory-Efficient and Feature-Enhanced Network Architecture based on U-Net with Reduced Skip-Connections
• Unconstrained Text Detection in Manga
• The Best of Both Worlds: a Framework for Combining Degradation Prediction with High Performance Super-Resolution Networks
• LIRA: Lifelong Image Restoration from Unknown Blended Distortions
• Exploiting Aliasing for Manga Restoration
• Adaptive Densely Connected Super-Resolution Reconstruction
• Bi-GANs-ST for Perceptual Image Super-resolution
• Deep Adaptive Inference Networks for Single Image Super-Resolution
• Painting Style-Aware Manga Colorization Based on Generative Adversarial Networks
• Joint Demosaicing and Super-Resolution (JDSR): Network Design and Perceptual Optimization
• Multi-Grid Back-Projection Networks
• Distilling with Residual Network for Single Image Super Resolution
• Back-Projection Pipeline
• USB: Universal-Scale Object Detection Benchmark
• edge-SR: Super-Resolution For The Masses