mlsanityData to 14 Oct 2026

CLIPasso: Semantically-Aware Object Sketching

arXiv 2202.05822 ↗First posted 11 Feb 2022cs.GR cs.AI cs.CVcited by 57

Not on the map. Why?

Abstract (arXiv)

Abstraction is at the heart of sketching due to the simple and minimal nature of line drawings. Abstraction entails identifying the essential visual properties of an object or scene, which requires semantic understanding and prior knowledge of high-level concepts. Abstract depictions are therefore challenging for artists, and even more so for machines. We present CLIPasso, an object sketching method that can achieve different levels of abstraction, guided by geometric and semantic simplifications. While sketch generation methods often rely on explicit sketch datasets for training, we utilize the remarkable ability of CLIP (Contrastive-Language-Image-Pretraining) to distill semantic concepts from sketches and images alike. We define a sketch as a set of B'ezier curves and use a differentiable rasterizer to optimize the parameters of the curves directly with respect to a CLIP-based perceptual loss. The abstraction degree is controlled by varying the number of strokes. The generated sketches demonstrate multiple levels of abstraction while maintaining recognizability, underlying structure, and essential visual components of the subject drawn.

Key facts. Cited by 57 papers in the map (data through 14 Oct 2026). Builds on 34 of its 58 references that are in the map. First posted on arXiv 11 Feb 2022.

Builds on

34 of 58 references.

References · 34

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  5. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  6. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  7. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,179
  8. 2020U2-Net: Going Deeper with Nested U-Structure for Salient Object Detectioncited by 412
  9. 2021Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformerscited by 320
  10. 2017A Neural Representation of Sketch Drawingscited by 313
  11. 2021CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoderscited by 187
  12. 2020Sketchformer: Transformer-based Representation for Sketched Structurecited by 78
22 more
  1. 2018Synthesizing Programs for Images using Reinforced Adversarial Learningcited by 72
  2. 2019Photo-Sketching: Inferring Contour Drawings from Imagescited by 68
  3. 2020SketchyCOCO: Image Generation from Freehand Scene Sketchescited by 67
  4. 2020Deep Learning for Free-Hand Sketch: A Surveycited by 59
  5. 2018Learning to Sketch with Shortcut Cycle Consistencycited by 47
  6. 2020Sketch-BERT: Learning Sketch Bidirectional Encoder Representation from Transformers by Self-supervised Learning of Sketch Gestaltcited by 42
  7. 2021Modern Evolution Strategies for Creativity: Fitting Concrete Images and Abstract Conceptscited by 40
  8. 2018Learning Deep Sketch Abstractioncited by 36
  9. 2020Why Do Line Drawings Work? A Realism Hypothesiscited by 28
  10. 2021Learning to Draw: Emergent Communication through Sketchingcited by 23
  11. 2019Unsupervised Doodling and Painting with Improved SPIRALcited by 21
  12. 2021Differentiable Drawing and Sketchingcited by 21
  13. 2017Sketch-pix2seq: a Model to Generate Sketches of Multiple Categoriescited by 20
  14. 2021SketchLattice: Latticed Representation for Sketch Manipulationcited by 19
  15. 2015Free-hand Sketch Synthesis with Deformable Stroke Modelscited by 16
  16. 2021Emergent Graphical Conventions in a Visual Communication Gamecited by 16
  17. 2019Pragmatic inference and visual abstraction enable contextual flexibility during visual communicationcited by 14
  18. 2020Synthesizing human-like sketches from natural images using a conditional convolutional decodercited by 13
  19. 2019Teaching GANs to Sketch in Vector Formatcited by 8
  20. 2018Line Drawings from 3D Modelscited by 7
  21. 2021Visual communication of object concepts at different levels of abstractioncited by 5
  22. 2021The Role of Edges in Line Drawing Perceptioncited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 21; 2024: 14; 2025: 13; 2026: 7.

57 papers.

Sort:

By area:

  1. 2023Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspectivecited by 280
  2. 2023Review of Large Vision Models and Visual Prompt Engineeringcited by 77
  3. 2023Word-As-Image for Semantic Typographycited by 63
  4. 2023Concept Decomposition for Visual Exploration and Inspirationcited by 61
  5. 2023RePrompt: Automatic Prompt Editing to Refine AI-Generative Art Towards Precise Expressionscited by 43
  6. 2023CLIP in Medical Imaging: A Surveycited by 40
  7. 2023NOPE: Novel Object Pose Estimation from a Single Imagecited by 38
  8. 2023CLIP-S4: Language-Guided Self-Supervised Semantic Segmentationcited by 34
  9. 2024Text-to-Vector Generation with Neural Path Representationcited by 33
  10. 2023Lossless Adaptation of Pretrained Vision Models For Robotic Manipulationcited by 29
  11. 2022Non-Contrastive Learning Meets Language-Image Pre-Trainingcited by 25
  12. 20243Doodle: Compact Abstraction of Objects with 3D Strokescited by 21
38 more
  1. 2023What Can Human Sketches Do for Object Detection?cited by 19
  2. 2023Wired Perspectives: Multi-View Wire Art Embraces Generative AIcited by 17
  3. 2025SVGenius: Benchmarking LLMs in SVG Understanding, Editing and Generationcited by 16
  4. 2023Doodle Your 3D: From Abstract Freehand Sketches to Precise 3D Shapescited by 14
  5. 2025SwiftSketch: A Diffusion Model for Image-to-Vector Sketch Generationcited by 14
  6. 2025SVGen: Interpretable Vector Graphics Generation with Large Language Modelscited by 14
  7. 2023CLIPAG: Towards Generator-Free Text-to-Image Generationcited by 12
  8. 2025Multi-Object Sketch Animation with Grouping and Motion Trajectory Priorscited by 9
  9. 2023SENS: Part-Aware Sketch-based Implicit Neural Shape Modelingcited by 8
  10. 2024FontCLIP: A Semantic Typography Visual-Language Model for Multilingual Font Applicationscited by 8
  11. 2024Freehand Sketch Generation from Mechanical Componentscited by 8
  12. 2024VectorPainter: Advanced Stylized Vector Graphics Synthesis Using Stroke-Style Priorscited by 7
  13. 2022Zero-Shot Multi-Modal Artist-Controlled Retrieval and Exploration of 3D Object Setscited by 5
  14. 2023Learning Geometry-aware Representations by Sketchingcited by 5
  15. 2023Text-Guided Vector Graphics Customizationcited by 5
  16. 2023Generative Escher Meshescited by 5
  17. 2024Semi-supervised reference-based sketch extraction using a contrastive learning frameworkcited by 5
  18. 2023AlteredAvatar: Stylizing Dynamic 3D Avatars with Fast Style Adaptationcited by 4
  19. 2024Stylized Face Sketch Extraction via Generative Prior with Limited Datacited by 4
  20. 2024Sketch3D: Style-Consistent Guidance for Sketch-to-3D Generationcited by 4
  21. 2025Instance Segmentation of Scene Sketches Using Natural Image Priorscited by 4
  22. 2025Neural Image Abstraction Using Long Smoothing B-Splinescited by 4
  23. 2024CraftSVG: Multi-Object Text-to-SVG Synthesis via Layout Guided Diffusioncited by 3
  24. 2024SD-πXL: Generating Low-Resolution Quantized Imagery via Score Distillationcited by 3
  25. 2026Stroke of Surprise: Progressive Semantic Illusions in Vector Sketchingcited by 3
  26. 2026Deep Sketch-Based 3D Modeling: A Surveycited by 3
  27. 2024DeepIcon: A Hierarchical Network for Layer-wise Icon Vectorizationcited by 2
  28. 2025AutoSketch: VLM-assisted Style-Aware Vector Sketch Completioncited by 2
  29. 2025Style Customization of Text-to-Vector Generation with Image Diffusion Priorscited by 2
  30. 2023The Contemporary Art of Image Search: Iterative User Intent Expansion via Vision-Language Modelcited by 1
  31. 2024SketchRef: a Multi-Task Evaluation Benchmark for Sketch Synthesiscited by 1
  32. 2024Sketching With Your Voice: "Non-Phonorealistic" Rendering of Sounds via Vocal Imitationcited by 1
  33. 2025IlluSign: Illustrating Sign Language Videos by Leveraging the Attention Mechanismcited by 1
  34. 2025StableSketcher: Enhancing Diffusion Model for Pixel-based Sketch Generation via Visual Question Answering Feedbackcited by 1
  35. 2023Learning Dense Correspondences between Photos and Sketchescited by 0
  36. 2023CLIPDraw++: Text-to-Sketch Synthesis with Simple Primitivescited by 0
  37. 2024A Formalization of Image Vectorization by Region Mergingcited by 0
  38. 2025An Active Contour Model for Silhouette Vectorization using B'ezier Curvescited by 0

50 most cited of 57 All 57 (JSON)