mlsanityData to 7 Oct 2026

Learning to generate line drawings that convey geometry and semantics

arXiv 2203.12691 ↗First posted 23 Mar 2022cs.CV cs.GRcited by 82

Not on the map. Why?

Abstract (arXiv)

This paper presents an unpaired method for creating line drawings from photographs. Current methods often rely on high quality paired datasets to generate line drawings. However, these datasets often have limitations due to the subjects of the drawings belonging to a specific domain, or in the amount of data collected. Although recent work in unsupervised image-to-image translation has shown much progress, the latest methods still struggle to generate compelling line drawings. We observe that line drawings are encodings of scene information and seek to convey 3D shape and semantic meaning. We build these observations into a set of objectives and train an image translation to map photographs into line drawings. We introduce a geometry loss which predicts depth information from the image features of a line drawing, and a semantic loss which matches the CLIP features of a line drawing with its corresponding photograph. Our approach outperforms state-of-the-art unpaired image translation and line drawing generation methods on creating line drawings from arbitrary photographs. For code and demo visit our webpage carolineec.github.io/informative_drawings

Key facts. Cited by 82 papers in the map (data through 7 Oct 2026). Builds on 53 of its 88 references that are in the map. First posted on arXiv 23 Mar 2022.

Builds on

53 of 88 references.

References · 53

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  6. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  7. 2022Generative Adversarial Networkscited by 5,603
  8. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  9. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  10. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  11. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  12. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
38 more
  1. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  2. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  3. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,176
  4. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  5. 2016Least Squares Generative Adversarial Networkscited by 1,000
  6. 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 990
  7. 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
  8. 2015Holistically-Nested Edge Detectioncited by 590
  9. 2017A Neural Representation of Sketch Drawingscited by 311
  10. 2017DualGAN: Unsupervised Dual Learning for Image-to-Image Translationcited by 310
  11. 2017Learning to Discover Cross-Domain Relations with Generative Adversarial Networkscited by 278
  12. 2017Photographic Image Synthesis with Cascaded Refinement Networkscited by 223
  13. 2019U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translationcited by 186
  14. 2021CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoderscited by 186
  15. 2016Single-Image Depth Perception in the Wildcited by 179
  16. 2021Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Mergingcited by 104
  17. 2018Synthesizing Programs for Images using Reinforced Adversarial Learningcited by 72
  18. 2019Learning to Paint With Model-based Deep Reinforcement Learningcited by 70
  19. 2019Photo-Sketching: Inferring Contour Drawings from Imagescited by 67
  20. 2020TSIT: A Simple and Versatile Framework for Image-to-Image Translationcited by 64
  21. 2017CycleGAN, a Master of Steganographycited by 63
  22. 2021Paint Transformer: Feed Forward Neural Painting with Stroke Predictioncited by 61
  23. 2020Reusing Discriminators for Encoding: Towards Unsupervised Image-to-Image Translationcited by 60
  24. 2020Unpaired Image-to-Image Translation using Adversarial Consistency Losscited by 43
  25. 2020B'ezierSketch: A generative model for scalable vector sketchescited by 43
  26. 2019Breaking the cycle -- Colleagues are all you needcited by 40
  27. 2017ComboGAN: Unrestrained Scalability for Image Domain Translationcited by 37
  28. 2019Deep Parametric Shape Predictions using Distance Fieldscited by 30
  29. 2019Neural Painters: A learned differentiable constraint for generating brushstroke paintingscited by 28
  30. 2020Why Do Line Drawings Work? A Realism Hypothesiscited by 28
  31. 2019Im2Pencil: Controllable Pencil Illustration from Photographscited by 18
  32. 2020SketchEmbedNet: Learning Novel Concepts by Imitating Drawingscited by 18
  33. 2021SPatchGAN: A Statistical Feature Based Discriminator for Unsupervised Image-to-Image Translationcited by 17
  34. 2018Vectorization of Line Drawings via PolyVector Fieldscited by 16
  35. 2020Neural Contours: Learning to Draw Lines from 3D Shapescited by 15
  36. 2021Unaligned Image-to-Image Translation by Learning to Reweightcited by 13
  37. 2021Neural Strokes: Stylized Line Drawing of 3D Shapescited by 13
  38. 2017Mastering Sketching: Adversarial Augmentation for Structured Predictioncited by 12

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 24; 2024: 18; 2025: 25; 2026: 11.

82 papers.

Sort:

By area:

  1. 2025VACE: All-in-One Video Creation and Editingcited by 467
  2. 2023DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Datacited by 322
  3. 2023CCEdit: Creative and Controllable Video Editing via Diffusion Modelscited by 80
  4. 2022CLIPascene: Scene Sketching with Different Types and Levels of Abstractioncited by 63
  5. 2024ACE: All-round Creator and Editor Following Instructions via Diffusion Transformercited by 56
  6. 2023DiffSketcher: Text Guided Vector Sketch Synthesis through Latent Diffusion Modelscited by 54
  7. 2023Breathing Life Into Sketches Using Text-to-Video Priorscited by 47
  8. 2025PhysAnimator: Physics-Guided Generative Cartoon Animationcited by 40
  9. 2025IMAGGarment: Fine-Grained Garment Generation for Controllable Fashion Designcited by 36
  10. 2024SketchAgent: Language-Driven Sequential Sketch Generationcited by 30
  11. 2024It's All About Your Sketch: Democratising Sketch Control in Diffusion Modelscited by 28
  12. 2023Control3Diff: Learning Controllable 3D Diffusion Models from Single-view Imagescited by 27
38 more
  1. 20233D-aware Conditional Image Synthesiscited by 24
  2. 2024AniDoc: Animation Creation Made Easiercited by 22
  3. 2023MeDM: Mediating Image Diffusion Models for Video-to-Video Translation with Temporal Correspondence Guidancecited by 17
  4. 2024Learning Continuous 3D Words for Text-to-Image Generationcited by 16
  5. 2025SketchVideo: Sketch-based Video Generation and Editingcited by 15
  6. 2023Exploiting Unlabelled Photos for Stronger Fine-Grained SBIRcited by 14
  7. 2023Doodle Your 3D: From Abstract Freehand Sketches to Precise 3D Shapescited by 14
  8. 2024Geospecific View Generation -- Geometry-Context Aware High-resolution Ground View Inference from Satellite Viewscited by 13
  9. 2024You'll Never Walk Alone: A Sketch and Text Duet for Fine-Grained Image Retrievalcited by 12
  10. 2025LayerAnimate: Layer-level Control for Animationcited by 12
  11. 2022Improving Fairness in Image Classification via Sketchingcited by 11
  12. 2025Frame Guidance: Training-Free Guidance for Frame-Level Control in Video Diffusion Modelscited by 11
  13. 2023Improving In-Context Learning in Diffusion Models with Visual Context-Modulated Promptscited by 9
  14. 2025MultiRef: Controllable Image Generation with Multiple Visual Referencescited by 9
  15. 2024FlipSketch: Flipping Static Drawings to Text-Guided Sketch Animationscited by 8
  16. 2022Content-Based Search for Deep Generative Modelscited by 7
  17. 2025LongAnimation: Long Animation Generation with Dynamic Global-Local Memorycited by 6
  18. 2022Vitruvio: 3D Building Meshes via Single Perspective Sketchescited by 5
  19. 2023Learning Geometry-aware Representations by Sketchingcited by 5
  20. 2023Reconstructive Latent-Space Neural Radiance Fields for Efficient 3D Scene Representationscited by 5
  21. 2024Semi-supervised reference-based sketch extraction using a contrastive learning frameworkcited by 5
  22. 2025Jodi: Unification of Visual Generation and Understanding via Joint Modelingcited by 5
  23. 2025AnimeColor: Reference-based Animation Colorization with Diffusion Transformerscited by 5
  24. 2023Towards Interactive Image Inpainting via Sketch Refinementcited by 4
  25. 2023Human-Inspired Facial Sketch Synthesis with Dynamic Adaptationcited by 4
  26. 2023Open Vocabulary Semantic Scene Sketch Understandingcited by 4
  27. 2024Representative Feature Extraction During Diffusion Process for Sketch Extraction with One Examplecited by 4
  28. 2024Stylized Face Sketch Extraction via Generative Prior with Limited Datacited by 4
  29. 2025MagicQuillV2: Precise and Interactive Image Editing with Layered Visual Cuescited by 4
  30. 2023Fine-Tuned but Zero-Shot 3D Shape Sketch View Similarity and Retrievalcited by 3
  31. 2023Emergent Communication in Interactive Sketch Question Answeringcited by 3
  32. 2025MixSA: Training-free Reference-based Sketch Extraction via Mixture-of-Self-Attentioncited by 3
  33. 2026Deep Sketch-Based 3D Modeling: A Surveycited by 3
  34. 2023Inventing art styles with no artistic training datacited by 2
  35. 2023Inversion-by-Inversion: Exemplar-based Sketch-to-Photo Synthesis via Stochastic Differential Equations without Trainingcited by 2
  36. 2024Do Generalised Classifiers really work on Human Drawn Sketches?cited by 2
  37. 2024CLIP4Sketch: Enhancing Sketch to Mugshot Matching through Dataset Augmentation using Diffusion Modelscited by 2
  38. 2024Enhanced Generative Data Augmentation for Semantic Segmentation via Stronger Guidancecited by 2

50 most cited of 82 All 82 (JSON)