Logo
Project Icon

Awesome-Sketch-Based-Applications

草图应用资源汇总 涵盖多领域前沿技术

Sketch-Based Applications图像合成图像编辑计算机视觉深度学习Github开源项目

这是一个全面的草图应用资源集合，涵盖图像合成、编辑、检索和3D建模等多个领域。项目汇总了大量相关研究论文和代码，包括自动合成、风格迁移和文本引导等最新技术。该资源为研究人员和开发者提供了探索草图应用前沿技术的重要参考。

GithubGithub论文论文
介绍相关项目

Awesome-Sketch-Based-Applications

A collection of sketch based applications.

Feel free to create a PR or an issue.

Outline

0. Survey

PaperSourceCode/Project Link
Deep Learning for Free-Hand Sketch: A SurveyTPAMI 2022[code]

1. Sketch Based Image Synthesis

1.1 Automatic Synthesis

  • Natural Image or Object
PaperSourceCode/Project Link
SketchyGAN: Towards Diverse and Realistic Sketch to Image SynthesisCVPR 2018[code]
Image Generation from Sketch Constraint Using Contextual GANECCV 2018[code] [project]
Multi-Instance Sketch to Image Synthesis With Progressive Generative Adversarial NetworksIEEE Access 2019
Interactive Sketch & Fill: Multiclass Sketch-to-Image TranslationICCV 2019[code] [project]
SketchyCOCO: Image Generation from Freehand Scene SketchesCVPR 2020[code]
Unsupervised Sketch-to-Photo SynthesisECCV 2020[code] [project]
Sketch Your Own GANICCV 2021[code] [webpage]
Adversarial Open Domain Adaption for Sketch-to-Photo SynthesisWACV 2022[code]
Customizing GAN Using Few-Shot SketchesACM MM 2022
DiffSketching: Sketch Control Image Synthesis with Diffusion ModelsBMVC 2022[code]
MaskSketch: Unpaired Structure-guided Masked Image GenerationCVPR 2023[project] [code]
Picture that Sketch: Photorealistic Image Generation from Abstract SketchesCVPR 2023[project] [code]
  • Human Face / Portrait / Body
PaperSourceCode/Project Link
LinesToFacePhoto: Face Photo Generation from Lines with Conditional Self-Attention Generative Adversarial NetworkACM MM 2019
DeepFaceDrawing: Deep Generation of Face Images from SketchesSIGGRAPH 2020[project] [code]
DeepFacePencil: Creating Face Images from Freehand SketchesACM MM 2020[project] [code]
Controllable Sketch-to-Image Translation for Robust Face SynthesisTIP 2021
DrawingInStyles: Portrait Image Generation and Editing with Spatially Conditioned StyleGANTVCG 2022
DeepPortraitDrawing: Generating Human Body Images from Freehand SketchesC&G 2023
Semantics-Preserving Sketch Embedding for Face GenerationTMM 2023[project] [code]
Parsing-Conditioned Anime Translation: A New Dataset and MethodTOG 2023[code]
Sketch2Human: Deep Human Generation with Disentangled Geometry and Appearance ConstraintsTVCG 2024
  • 3D image
PaperSourceCode/Project Link
3D-aware Conditional Image SynthesisCVPR 2023[project] [code]

1.2 Style-conditioned

PaperSourceCode/Project Link
TextureGAN: Controlling Deep Image Synthesis with Texture PatchesCVPR 2018[code]
Multimodal Unsupervised Image-to-Image TranslationECCV 2018[code]
SketchPatch: Sketch Stylization via Seamless Patch-level SynthesisSIGGRAPH Asia 2020
Self-Supervised Sketch-to-Image SynthesisAAAI 2021[code]
CoGS: Controllable Generation and Search from Sketch and StyleECCV 2022
Adaptively-Realistic Image Generation from Stroke and Sketch with Diffusion ModelWACV 2023[project] [code]
DemoCaricature: Democratising Caricature Generation with a Rough SketchCVPR 2024[project]
SMFS-GAN: Style-Guided Multi-class Freehand Sketch-to-Image SynthesisCGF 2024

1.3 Text-conditioned

PaperSourceCode/Project Link
Sketch-Guided Text-to-Image Diffusion ModelsSIGGRAPH 2023[project]
Adding Conditional Control to Text-to-Image Diffusion ModelsICCV 2023[code]
T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Modelsarxiv 23.02[code]
UniControl: A Unified Diffusion Model for Controllable Visual Generation In the WildNeurIPS 2023[code] [project]
Stable Doodle (ClipDrop)[demo]
CustomSketching: Sketch Concept Extraction for Sketch-based Image Synthesis and Editingarxiv 24.02
Block and Detail: Scaffolding Sketch-to-Image Generationarxiv 24.02
One-Step Image Translation with Text-to-Image Modelsarxiv 24.03[code]
It's All About Your Sketch: Democratising Sketch Control in Diffusion ModelsCVPR 2024[code]

2. Sketch Based Image Editing

  • Arbitrary Image
PaperSourceCode/Project Link
Free-Form Image Inpainting with Gated Convolution (DeepFill v2)ICCV 2019[project] [code]
Fashion Editing with Multi-scale Attention Normalization1906.00884
DeFLOCNet: Deep Image Editing via Flexible Low-level ControlsCVPR 2021[code]
DeepSIM: Image Shape Manipulation from a Single Augmented Training SampleICCV 2021[code] [project]
SketchEdit: Mask-Free Local Image Manipulation with Partial SketchesCVPR 2022[code] [project]
Draw2Edit: Mask-Free Sketch-Guided Image ManipulationACM MM 2023[code]
Towards Interactive Image Inpainting via Robust Sketch RefinementTMM 2024[code] [project]
  • Human Face / Portrait / Hair
PaperSourceCode/Project Link
FaceShop: Deep Sketch-based Face Image EditingSIGGRAPH 2018[project]
CaricatureShop: Personalized and Photorealistic Caricature SketchingTVCG 2018
Sparse, Smart Contours to Represent and Edit ImagesCVPR 2018[project]
Example-Guided Style-Consistent Image Synthesis from Semantic Labeling
相关项目
项目侧边栏1项目侧边栏2
推荐项目
Project Cover

豆包MarsCode

豆包 MarsCode 是一款革命性的编程助手，通过AI技术提供代码补全、单测生成、代码解释和智能问答等功能，支持100+编程语言，与主流编辑器无缝集成，显著提升开发效率和代码质量。

Project Cover

AI写歌

Suno AI是一个革命性的AI音乐创作平台，能在短短30秒内帮助用户创作出一首完整的歌曲。无论是寻找创作灵感还是需要快速制作音乐，Suno AI都是音乐爱好者和专业人士的理想选择。

Project Cover

白日梦AI

白日梦AI提供专注于AI视频生成的多样化功能，包括文生视频、动态画面和形象生成等，帮助用户快速上手，创造专业级内容。

Project Cover

有言AI

有言平台提供一站式AIGC视频创作解决方案，通过智能技术简化视频制作流程。无论是企业宣传还是个人分享，有言都能帮助用户快速、轻松地制作出专业级别的视频内容。

Project Cover

Kimi

Kimi AI助手提供多语言对话支持，能够阅读和理解用户上传的文件内容，解析网页信息，并结合搜索结果为用户提供详尽的答案。无论是日常咨询还是专业问题，Kimi都能以友好、专业的方式提供帮助。

Project Cover

讯飞绘镜

讯飞绘镜是一个支持从创意到完整视频创作的智能平台，用户可以快速生成视频素材并创作独特的音乐视频和故事。平台提供多样化的主题和精选作品，帮助用户探索创意灵感。

Project Cover

讯飞文书

讯飞文书依托讯飞星火大模型，为文书写作者提供从素材筹备到稿件撰写及审稿的全程支持。通过录音智记和以稿写稿等功能，满足事务性工作的高频需求，帮助撰稿人节省精力，提高效率，优化工作与生活。

Project Cover

阿里绘蛙

绘蛙是阿里巴巴集团推出的革命性AI电商营销平台。利用尖端人工智能技术，为商家提供一键生成商品图和营销文案的服务，显著提升内容创作效率和营销效果。适用于淘宝、天猫等电商平台，让商品第一时间被种草。

Project Cover

AIWritePaper论文写作

AIWritePaper论文写作是一站式AI论文写作辅助工具，简化了选题、文献检索至论文撰写的整个过程。通过简单设定，平台可快速生成高质量论文大纲和全文，配合图表、参考文献等一应俱全，同时提供开题报告和答辩PPT等增值服务，保障数据安全，有效提升写作效率和论文质量。

使用协议隐私政策广告服务
投诉举报邮箱: service@vectorlightyear.com
@2024 懂AI·鲁ICP备2024100362号-6·鲁公网安备37021002001498号