Home

Awesome

Awesome-Image-Colorization

Awesome

A collection of Deep Learning based Image Colorization papers and corresponding source code/demo program, including Automatic and User Guided (i.e. with User Interaction) colorization, as well as video colorization.

Feel free to create a PR or an issue. (Pull Request is preferred)

examples

Outline


1. Automatic Image Colorization

1.1 Software / Demo

NameAuthor/OwnerCode/Project Link
DeOldifyJason Antic[link]
Palette.fmEmil Wallner[link]

1.2 Papers

PaperSourceCode/Project Link
Learning Large-Scale Automatic Image ColorizationICCV 2015[project] [code]
Deep ColorizationICCV 2015
Learning Representations for Automatic ColorizationECCV 2016[project] [code]
Colorful Image ColorizationECCV 2016[project] [code]
Let there be Color!: Joint End-to-end Learning of Global and Local Image Priors for Automatic Image Colorization with Simultaneous ClassificationSIGGRAPH 2016[project] [code]
Learning Diverse Image ColorizationCVPR 2017[code]
Structural Consistency and Controllability for Diverse ColorizationECCV 2018
Coloring With Limited Data: Few-Shot Colorization via Memory Augmented NetworksCVPR 2019[project]<br/><br/> Unofficial:<br/> [code (PyTorch)]
ChromaGAN: Adversarial Picture Colorization with Semantic Class DistributionWACV 2020[code]
Instance-aware Image ColorizationCVPR 2020[code] [project]
Pixelated Semantic ColorizationIJCV 2020
Colorization TransformerICLR 2021[code]
Focusing on Persons: Colorizing Old Images Learning from Modern Historical MoviesACM MM 2021[code]
Towards Vivid and Diverse Image Colorization with Generative Color PriorICCV 2021[code]
SCSNet: An Efficient Paradigm for Learning Simultaneously Image Colorization and Super-Resolution (also reference based)AAAI 2022
Bridging the Domain Gap towards Generalization in Automatic ColorizationECCV 2022[code]
ColorFormer: Image Colorization via Color Memory assisted Hybrid-attention TransformerECCV 2022[code]
BigColor: Colorization using a Generative Color Prior for Natural ImagesECCV 2022[project] [code]
CT2: Colorization Transformer via Color TokensECCV 2022[code]
Disentangled Image Colorization via Global AnchorsSIGGRAPH Asia 2022[code] [project]
UniColor: A Unified Framework for Multi-Modal Colorization with Transformer (also multi-modal)SIGGRAPH Asia 2022[project]
Improved Diffusion-based Image Colorization via Piggybacked Modelsarxiv 23.04[project]
DDColor: Towards Photo-Realistic and Semantic-Aware Image Colorization via Dual DecodersICCV 2023[code] [project]
Diffusing Colors: Image Colorization with Text Guided Diffusion (also text-based)SIGGRAPH Asia 2023[project]
Automatic Controllable Colorization via ImaginationCVPR 2024[code] [project]
Control Color: Multimodal Diffusion-based Interactive Image Colorizationarxiv 24.02[code] [project]
MultiColor: Image Colorization by Learning from Multiple Color SpacesACM MM 2024
PaperSourceCode/Project Link
Region Assisted Sketch ColorizationTIP 2023

2. User Guided Image Colorization

2.1 Based on scribble

Image TypeNameAuthor/OwnerCode/Project Link
Line artPetalica Paint (Old version: PaintsChainer)Preferred Networks, Inc.[Petalica Paint (Online service)] [PaintsChainer V1 code]
Line artStyle2Paints (SEPA)Style2Paints Research[link]
Image TypePaperSourceCode/Project Link
MangaManga colorizationSIGGRAPH 2006[Project]
Line art / Sketch / MangaLazyBrush: Flexible Painting Tool for Hand-drawn CartoonsEurographics 2009[Project Home & Software] <br/><br/>Unofficial:<br/> [code(Matlab)]
Line art / SketchOutline Colorization through Tandem Adversarial Networks1704.08834[code]
Natural Gray-ScaleReal-Time User-Guided Image Colorization with Learned Deep PriorsSIGGRAPH 2017[project] [code1] [code2]
SketchScribbler: Controlling Deep Image Synthesis with Sketch and ColorCVPR 2017
Line art / SketchAuto-painter: Cartoon Image Generation from Sketch by Using Conditional Generative Adversarial NetworksNeurocomputing 2018[code]
Line artUser-Guided Deep Anime Line Art Colorization with Conditional Adversarial NetworksACM MM 2018[code]
Line artTwo-stage Sketch ColorizationSIGGRAPH Asia 2018[Project]
Line artUser-Guided Line Art Flat Filling with Split Filling MechanismCVPR 2021[Project] [code]
Line artDual Color Space Guided Sketch ColorizationTIP 2021
Natural Gray-ScaleiColoriT: Towards Propagating Local Hint to the Right Region in Interactive Colorization by Leveraging Vision TransformerWACV 2023[project] [code]

2.2 Based on reference image

Image TypePaperSourceCode/Project Link
MangaComicolorization: Semi-Automatic Manga ColorizationSIGGRAPH Asia 2017 Technical Briefs[code]
SketchTextureGAN: Controlling Deep Image Synthesis with Texture PatchesCVPR 2018[code]
Natural Gray-ScaleDeep Exemplar-based ColorizationSIGGRAPH 2018[code]
Natural Gray-ScaleExample-Based Colourization Via Dense Encoding Pyramids (also palette based)Pacific Graphics 2018[code]
Natural Gray-ScaleA Superpixel-based Variational Model for Image ColorizationTVCG 2019
Natural Gray-ScaleAutomatic Example-based Image Colourisation using Location-Aware Cross-Scale MatchingTIP 2019
Line art / SketchAdversarial Colorization Of Icons Based On Structure And Color ConditionsACM MM 2019[Code]
Line art / SketchReference-Based Sketch Image Colorization using Augmented-Self Reference and Dense Semantic CorrespondenceCVPR 2020[project]
Natural Gray-ScaleStylization-Based Architecture for Fast Deep Exemplar ColorizationCVPR 2020[code]
MangaManga Filling Style Conversion with Screentone Variational AutoencoderSIGGRAPH Asia 2020[project]
Line art / SketchColorization of Line Drawings with Empty PupilsPG 2020
Line art / SketchActive Colorization for Cartoon Line DrawingsTVCG 2020
Natural Gray-ScaleGray2ColorNet: Transfer More Colors from Reference ImageACM MM 2020
Line art / SketchLine Art Correlation Matching Feature Transfer Network for Automatic Animation ColorizationWACV 2021
Natural Gray-ScaleGlobally and Locally Semantic Colorization via Exemplar-Based Broad-GANTIP 2021
Natural Gray-ScaleYes, "Attention Is All You Need", for Exemplar based ColorizationACM MM 2021
Natural Gray-ScaleSCSNet: An Efficient Paradigm for Learning Simultaneously Image Colorization and Super-Resolution (also automatic)AAAI 2022
Line art / SketchStyle-Structure Disentangled Features and Normalizing Flows for Diverse Icon ColorizationCVPR 2022
Line art / SketchEliminating Gradient Conflict in Reference-based Line-Art ColorizationECCV 2022[code]
Natural Gray-ScaleSemantic-Sparse Colorization Network for Deep Exemplar-based ColorizationECCV 2022
Line art / SketchSelf-driven Dual-path Learning for Reference-based Line Art Colorization under Limited DataTCSVT 2023
Natural Gray-ScaleUnsupervised Deep Exemplar Colorization via Pyramid Dual Non-local AttentionTIP 2023[code]
Line art / SketchFlexIcon: Flexible Icon Colorization via Guided Images and Palettes (also palette based)ACM MM 2023
Line art / SketchAnimeDiffusion: Anime Face Line Drawing Colorization via Diffusion ModelsTVCG 2024[code]
Natural Gray-ScaleLightweight Deep Exemplar Colorization via Semantic Attention-Guided Laplacian PyramidTVCG 2024

2.3 Based on palette

Image TypePaperSourceCode/Project Link
Natural ImagePalette-based Photo RecoloringSIGGRAPH 2015[project]
Natural Gray-ScaleColoring with Words: Guiding Image Colorization Through Text-based Palette Generation (also text based)ECCV 2018[code]
Natural Gray-ScaleExample-Based Colourization Via Dense Encoding Pyramids (also reference based)Pacific Graphics 2018[code]
Natural Gray-ScalePalGAN: Image Colorization with Palette Generative Adversarial NetworksECCV 2022[code]
Line art / SketchFlexIcon: Flexible Icon Colorization via Guided Images and Palettes (also reference based)ACM MM 2023
Line art / SketchSketchDeco: Decorating B&W Sketches with Colourarxiv 24.05[code] [webpage]

2.4 Based on language or text

Image TypePaperSourceCode/Project Link
Natural Gray-Scale / SketchLanguage-Based Image Editing with Recurrent Attentive ModelsCVPR 2018[code]
Natural Gray-ScaleColoring with Words: Guiding Image Colorization Through Text-based Palette Generation (also palette based)ECCV 2018[code]
Natural Gray-ScaleLearning to Color from LanguageNAACL 2018[code]
Line artTag2Pix: Line Art Colorization Using Text Tag With SECat and Changing LossICCV 2019[code] [code2 (GUI)]
Scene SketchLanguage-based Colorization of Scene SketchesSIGGRAPH Asia 2019[code] [project]
Line artLine Art Colorization Based on Explicit Region SegmentationPacific Graphics 2021[code]
Natural Gray-ScaleL-CoDe: Language-based Colorization using Color-object Decoupled ConditionsAAAI 2022[code]
Natural Gray-ScaleL-CoDer: Language-based Colorization with Color-object Decoupling TransformerECCV 2022[code]
Natural Gray-ScaleL-CoIns: Language-based Colorization with Instance AwarenessCVPR 2023
Natural Gray-ScaleL-CAD: Language-based Colorization with Any-level DescriptionsNeurIPS 2023[code]
SketchAdding Conditional Control to Text-to-Image Diffusion ModelsICCV 2023[code]
Natural Gray-ScaleDiffusing Colors: Image Colorization with Text Guided DiffusionSIGGRAPH Asia 2023[project]

2.5 Multi-modal

Image TypePaperInputSourceCode/Project Link
Natural Gray-ScaleInteractive Deep Colorization Using Simultaneous Global and Local Inputsstroke + paletteICASSP 2019
Natural Gray-ScaleUniColor: A Unified Framework for Multi-Modal Colorization with Transformerstroke + exemplar + textSIGGRAPH Asia 2022[project]
Line artTwo-Step Training: Adjustable Sketch Colourization via Reference Image and Text Tagexemplar + textCGF 2023[code]
Natural Gray-ScaleControl Color: Multimodal Diffusion-based Interactive Image Colorizationtext, stroke, exemplararxiv 24.02[code] [project]
Natural Gray-ScaleVersatile Vision Foundation Model for Image and Video Colorizationtext, scribble, exemplarSIGGRAPH 2024

2.6 Interactive Colorization

Image TypePaperSourceCode/Project Link
Line artGuiding Users to Where to Give Color Hints for Efficient Interactive Sketch Colorization via Unsupervised Region PrioritizationWACV 2023

3. Techniques of Improving Image Colorization

PaperSourceCode/Project Link
Deep Edge-Aware Interactive Colorization against Color-Bleeding EffectsICCV 2021[project] [code(metric)]
Line Art Colorization Based on Explicit Region SegmentationPacific Graphics 2021[code]
FlatGAN: A Holistic Approach for Robust Flat-Coloring in High-Definition with Understanding Line DiscontinuityACM MM 2023[code]

4. Video Colorization

4.0 Survey

Image TypePaperSourceCode/Project Link
Video Colorization: A SurveyJCST 2024

4.1 Automatically

Image TypePaperSourceCode/Project Link
Natural Gray-ScaleFully Automatic Video Colorization with Self-Regularization and DiversityCVPR 2019[code]

4.2 Based on reference

Image TypePaperSourceCode/Project Link
Natural Gray-ScaleSwitchable Temporal Propagation NetworkECCV 2018
Natural Gray-ScaleTracking Emerges by Colorizing VideosECCV 2018[code]
Natural Gray-ScaleDeep Exemplar-based Video ColorizationCVPR 2019[code]
Natural Gray-ScaleDeepRemaster: Temporal Source-Reference Attention Networks for Comprehensive Video EnhancementSIGGRAPH Asia 2019[code] [project]
Natural Gray-ScaleReference-Based Video Colorization with Spatiotemporal Correspondence2011.12528
Line artThe Animation Transformer: Visual Correspondence via Segment MatchingICCV 2021[App]
Line artLine Art Correlation Matching Feature Transfer Network for Automatic Animation ColorizationWACV 2021
Line artReference-Based Deep Line Art Video ColorizationTVCG 2022
Line artLearning Inclusion Matching for Animation Paint Bucket ColorizationCVPR 2024[webpage] [code]
Natural Gray-ScaleBiSTNet: Semantic Image Prior Guided Bidirectional Temporal Feature Fusion for Deep Exemplar-based Video ColorizationTPAMI 2024[code] [project]
Natural Gray-ScaleExemplar-based Video Colorization with Long-term Spatiotemporal DependencyKBS 2024
Natural Gray-ScaleColorMNet: A Memory-based Deep Spatial-Temporal Feature Propagation Network for Video Colorizationarxiv 24.04[code] [project]
Line artToonCrafter: Generative Cartoon Interpolationarxiv 24.05[code] [webpage]

4.3 Based on scribble

Image TypePaperSourceCode/Project Link
Natural Gray-ScaleSVCNet: Scribble-based Video Colorization Network with Temporal AggregationTIP 2023[code]

4.4 Based on text

Image TypePaperSourceCode/Project Link
Natural Gray-ScaleVideo Colorization with Pre-trained Text-to-Image Diffusion Modelsarxiv 23.06[code] [project]
Natural Gray-ScaleTowards Photorealistic Video Colorization via Gated Color-Guided Image Diffusion ModelsACM MM 2024