# Neural Contours: Learning to Draw Lines from 3D Shapes

arXiv: https://arxiv.org/abs/2003.10333 · HTML: https://mlsanity.com/paper/2003.10333/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Mar 2020.

## Built on by (most cited first, 15 of 15)

- [Learning to generate line drawings that convey geometry and semantics](https://mlsanity.com/paper/2203.12691/) (2022)
- [3Doodle: Compact Abstraction of Objects with 3D Strokes](https://mlsanity.com/paper/2402.03690/) (2024)
- [VecFusion: Vector Font Generation with Diffusion](https://mlsanity.com/paper/2312.10540/) (2023)
- [Neural Strokes: Stylized Line Drawing of 3D Shapes](https://mlsanity.com/paper/2110.03900/) (2021)
- [Freehand Sketch Generation from Mechanical Components](https://mlsanity.com/paper/2408.05966/) (2024)
- ['CADSketchNet' -- An Annotated Sketch dataset for 3D CAD Model Retrieval with Deep Neural Networks](https://mlsanity.com/paper/2107.06212/) (2021)
- [Vitruvio: 3D Building Meshes via Single Perspective Sketches](https://mlsanity.com/paper/2210.13634/) (2022)
- [WIR3D: Visually-Informed and Geometry-Aware 3D Shape Abstraction](https://mlsanity.com/paper/2505.04813/) (2025)
- [The Role of Edges in Line Drawing Perception](https://mlsanity.com/paper/2101.09376/) (2021)
- [Interactive Sketching of Mannequin Poses](https://mlsanity.com/paper/2212.07098/) (2022)
- [Occlusion-robust Stylization for Drawing-based 3D Animation](https://mlsanity.com/paper/2508.00398/) (2025)
- [SketchCleanNet -- A deep learning approach to the enhancement and correction of query sketches for a 3D CAD model retrieval system](https://mlsanity.com/paper/2207.00732/) (2022)
- [DifferSketching: How Differently Do People Sketch 3D Objects?](https://mlsanity.com/paper/2209.08791/) (2022)
- [Empowering Vector Graphics with Consistently Arbitrary Viewing and View-dependent Visibility](https://mlsanity.com/paper/2505.21377/) (2025)
- [ShadowDraw: From Any Object to Shadow-Drawing Compositional Art](https://mlsanity.com/paper/2512.05110/) (2025)

## Abstract (arXiv)

This paper introduces a method for learning to generate line drawings from 3D models. Our architecture incorporates a differentiable module operating on geometric features of the 3D model, and an image-based module operating on view-based shape representations. At test time, geometric and view-based reasoning are combined with the help of a neural module to create a line drawing. The model is trained on a large number of crowdsourced comparisons of line drawings. Experiments demonstrate that our method achieves significant improvements in line drawing over the state-of-the-art when evaluated on standard benchmarks, resulting in drawings that are comparable to those produced by experienced human artists.