# DifferSketching: How Differently Do People Sketch 3D Objects?

arXiv: https://arxiv.org/abs/2209.08791 · HTML: https://mlsanity.com/paper/2209.08791/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 52 references that are in the map.
- First posted on arXiv 19 Sep 2022.

## Builds on (most cited first, 18 of 18)

- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [A Point Set Generation Network for 3D Object Reconstruction from a Single Image](https://mlsanity.com/paper/1612.00603/) (2016)
- [Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images](https://mlsanity.com/paper/1804.01654/) (2018)
- [Holistically-Nested Edge Detection](https://mlsanity.com/paper/1504.06375/) (2015)
- [3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction](https://mlsanity.com/paper/1604.00449/) (2016)
- [A Neural Representation of Sketch Drawings](https://mlsanity.com/paper/1704.03477/) (2017)
- [Richer Convolutional Features for Edge Detection](https://mlsanity.com/paper/1612.02103/) (2016)
- [Sketch2Model: View-Aware 3D Modeling from Single Free-Hand Sketches](https://mlsanity.com/paper/2105.06663/) (2021)
- [Sketch2Mesh: Reconstructing and Editing 3D Shapes from Sketches](https://mlsanity.com/paper/2104.00482/) (2021)
- [DeepEdge: A Multi-Scale Bifurcated Deep Network for Top-Down Contour Detection](https://mlsanity.com/paper/1412.1123/) (2014)
- [3D Shape Reconstruction from Sketches via Multi-view Convolutional Networks](https://mlsanity.com/paper/1707.06375/) (2017)
- [3D Sketching using Multi-View Deep Volumetric Prediction](https://mlsanity.com/paper/1707.08390/) (2017)
- [Free-hand Sketch Synthesis with Deformable Stroke Models](https://mlsanity.com/paper/1510.02644/) (2015)
- [DeepSketch2Face: A Deep Learning Based Sketching System for 3D Face and Caricature Modeling](https://mlsanity.com/paper/1706.02042/) (2017)
- [Neural Contours: Learning to Draw Lines from 3D Shapes](https://mlsanity.com/paper/2003.10333/) (2020)
- [Deep Sketch-Based Modeling: Tips and Tricks](https://mlsanity.com/paper/2011.06133/) (2020)
- [SketchDesc: Learning Local Sketch Descriptors for Multi-view Correspondence](https://mlsanity.com/paper/2001.05744/) (2020)

## Built on by (most cited first, 2 of 2)

- [SwiftSketch: A Diffusion Model for Image-to-Vector Sketch Generation](https://mlsanity.com/paper/2502.08642/) (2025)
- [Deep Sketch-Based 3D Modeling: A Survey](https://mlsanity.com/paper/2603.03287/) (2026)

## Abstract (arXiv)

Multiple sketch datasets have been proposed to understand how people draw 3D objects. However, such datasets are often of small scale and cover a small set of objects or categories. In addition, these datasets contain freehand sketches mostly from expert users, making it difficult to compare the drawings by expert and novice users, while such comparisons are critical in informing more effective sketch-based interfaces for either user groups. These observations motivate us to analyze how differently people with and without adequate drawing skills sketch 3D objects. We invited 70 novice users and 38 expert users to sketch 136 3D objects, which were presented as 362 images rendered from multiple views. This leads to a new dataset of 3,620 freehand multi-view sketches, which are registered with their corresponding 3D objects under certain views. Our dataset is an order of magnitude larger than the existing datasets. We analyze the collected data at three levels, i.e., sketch-level, stroke-level, and pixel-level, under both spatial and temporal characteristics, and within and across groups of creators. We found that the drawings by professionals and novices show significant differences at stroke-level, both intrinsically and extrinsically. We demonstrate the usefulness of our dataset in two applications: (i) freehand-style sketch synthesis, and (ii) posing it as a potential benchmark for sketch-based 3D reconstruction. Our dataset and code are available at https://chufengxiao.github.io/DifferSketching/.