Lune

CVPR2021Top-tier venue

Cloud2Curve: Generation and Vectorization of Parametric Sketches

Ayan Das, Yongxin Yang, Timothy M. Hospedales, Tao Xiang, Yi-Zhe Song

Abstract

Analysis of human sketches in deep learning has advanced immensely through the use of waypoint-sequences rather than raster-graphic representations. We further aim to model sketches as a sequence of low-dimensional parametric curves. To this end, we propose an inverse graphics framework capable of approximating a raster or waypoint based stroke encoded as a point-cloud with a variable-degree Bézier curve. Building on this module, we present Cloud2Curve, a generative model for scalable high-resolution vector sketches that can be trained end-toend using point-cloud data alone. As a consequence, our model is also capable of deterministic vectorization which can map novel raster or waypoint based sketches to their corresponding high-resolution scalable Bézier equivalent. We evaluate the generation and vectorization capabilities of our model on Quick, Draw! and K-MNIST datasets.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

12 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • filtered.ink: Creating Dynamic Illustrations with SVG Filters cites A Learned Representation for Scalable Vector Graphics
  • filtered.ink: Creating Dynamic Illustrations with SVG Filters cites DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation
  • SketchGen: Generating Constrained CAD Sketches cites A Learned Representation for Scalable Vector Graphics
  • SketchGen: Generating Constrained CAD Sketches cites DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation
  • Deep Sketch Vectorization via Implicit Surface Extraction cites A Learned Representation for Scalable Vector Graphics
  • Deep Sketch Vectorization via Implicit Surface Extraction cites DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation
  • CoSE: Compositional Stroke Embeddings cites Sketchformer: Transformer-Based Representation for Sketched Structure
  • Neural Recognition of Dashed Curves with Gestalt Law of Continuity cites DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation
  • Finding Badly Drawn Bunnies cites Sketch Less for More: On-the-Fly Fine-Grained Sketch-Based Image Retrieval
  • Finding Badly Drawn Bunnies cites Sketchformer: Transformer-Based Representation for Sketched Structure
  • DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation cites A Learned Representation for Scalable Vector Graphics
  • DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation cites Sketchformer: Transformer-Based Representation for Sketched Structure
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers12

  1. SketchGen: Generating Constrained CAD SketchesWamiq Reyaz Para, Shariq Farooq Bhat, Paul Guerrero, Tom Kelly et al.NeurIPS 2021 · 114 citations
  2. Deep Sketch Vectorization via Implicit Surface ExtractionChuan Yan, Yong Li, Deepali Aneja, Matthew Fisher et al.SIGGRAPH 2024 · 12 citations
  3. filtered.ink: Creating Dynamic Illustrations with SVG FiltersTongyu Zhou, Connie Liu, Joshua Kong Yang, Jeff HuangCHI 2023 · 11 citations
  4. Neural Recognition of Dashed Curves with Gestalt Law of ContinuityHanyuan Liu, Chengze Li, Xueting Liu, Tien-Tsin WongCVPR 2022 · 4 citations
  5. Finding Badly Drawn BunniesLan Yang, Kaiyue Pang, Honggang Zhang, Yi-Zhe SongCVPR 2022 · 4 citations

Builds on5

  1. DeepSVG: A Hierarchical Generative Network for Vector Graphics AnimationAlexandre Carlier, Martin Danelljan, Alexandre Alahi, Radu TimofteNeurIPS 2020 · 247 citations
  2. A Learned Representation for Scalable Vector GraphicsRaphael Gontijo Lopes, David Ha, Douglas Eck, Jonathon ShlensICCV 2019 · 153 citations
  3. CoSE: Compositional Stroke EmbeddingsEmre Aksan, Thomas Deselaers, Andrea Tagliasacchi, Otmar HilligesNeurIPS 2020 · 37 citations
  4. Sketch Less for More: On-the-Fly Fine-Grained Sketch-Based Image RetrievalAyan Kumar Bhunia, Yongxin Yang, Timothy M. Hospedales, Tao Xiang et al.CVPR 2020
  5. Sketchformer: Transformer-Based Representation for Sketched StructureLeo Sampaio Ferraz Ribeiro, Tu Bui, John P. Collomosse, Moacir PontiCVPR 2020

Related papers

  1. 2D Gaussian Splatting for Bézier Spline Line Art VectorizationTianhao Chen, Clara Fernandez-Labrador, Marteinn Oskarsson, Chuck Tappan et al.SIGGRAPH 2026
  2. Towards Layer-wise Image VectorizationXu Ma, Yuqian Zhou, Xingqian Xu, Bin Sun et al.CVPR 2022 · 56 citations
  3. PointFlow: 3D Point Cloud Generation With Continuous Normalizing FlowsGuandao Yang, Xun Huang, Zekun Hao, Ming-Yu Liu et al.ICCV 2019 · 794 citations
  4. End-to-End Line Drawing VectorizationHanyuan Liu, Chengze Li, Xueting Liu, Tien-Tsin WongAAAI 2022 · 11 citations
  5. Im2Vec: Synthesizing Vector Graphics Without Vector SupervisionPradyumna Reddy, Michaël Gharbi, Michal Lukác, Niloy J. MitraCVPR 2021
Dusk over the sea between two cliffs drawn in fine vertical lines