# Sketch Beautification: Learning Part Beautification and Structure Refinement for Sketches of Man-made Objects

arXiv: https://arxiv.org/abs/2306.05832 · HTML: https://mlsanity.com/paper/2306.05832/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 72 references that are in the map.
- First posted on arXiv 9 Jun 2023.

## Builds on (most cited first, 24 of 24)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [Learning Implicit Fields for Generative Shape Modeling](https://mlsanity.com/paper/1812.02822/) (2018)
- [PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization](https://mlsanity.com/paper/1905.05172/) (2019)
- [PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding](https://mlsanity.com/paper/1812.02713/) (2018)
- [A Neural Representation of Sketch Drawings](https://mlsanity.com/paper/1704.03477/) (2017)
- [BSP-Net: Generating Compact Meshes via Binary Space Partitioning](https://mlsanity.com/paper/1911.06971/) (2019)
- [PQ-NET: A Generative Part Seq2Seq Network for 3D Shapes](https://mlsanity.com/paper/1911.10949/) (2019)
- [Deformed Implicit Field: Modeling 3D Shapes with Learned Dense Correspondence](https://mlsanity.com/paper/2011.13650/) (2020)
- [SDM-NET: Deep Generative Network for Structured Deformable Mesh](https://mlsanity.com/paper/1908.04520/) (2019)
- [Sketchformer: Transformer-based Representation for Sketched Structure](https://mlsanity.com/paper/2002.10381/) (2020)
- [3D Shape Reconstruction from Sketches via Multi-view Convolutional Networks](https://mlsanity.com/paper/1707.06375/) (2017)
- [TransGaGa: Geometry-Aware Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1904.09571/) (2019)
- [Vectorization and Rasterization: Self-Supervised Learning for Sketch and Handwriting](https://mlsanity.com/paper/2103.13716/) (2021)
- [3D Sketching using Multi-View Deep Volumetric Prediction](https://mlsanity.com/paper/1707.08390/) (2017)
- [SketchMate: Deep Hashing for Million-Scale Human Sketch Retrieval](https://mlsanity.com/paper/1804.01401/) (2018)
- [Sketching without Worrying: Noise-Tolerant Sketch-Based Image Retrieval](https://mlsanity.com/paper/2203.14817/) (2022)
- [Fast Sketch Segmentation and Labeling with Deep Learning](https://mlsanity.com/paper/1807.11847/) (2018)
- [Deep Cross-modality Adaptation via Semantics Preserving Adversarial Learning for Sketch-based 3D Shape Retrieval](https://mlsanity.com/paper/1807.01806/) (2018)
- [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)

- [PC-NeRF: Parent-Child Neural Radiance Fields Using Sparse LiDAR Frames in Autonomous Driving Environments](https://mlsanity.com/paper/2402.09325/) (2024)
- [PC-NeRF: Parent-Child Neural Radiance Fields under Partial Sensor Data Loss in Autonomous Driving Environments](https://mlsanity.com/paper/2310.00874/) (2023)

## Abstract (arXiv)

We present a novel freehand sketch beautification method, which takes as input a freely drawn sketch of a man-made object and automatically beautifies it both geometrically and structurally. Beautifying a sketch is challenging because of its highly abstract and heavily diverse drawing manner. Existing methods are usually confined to the distribution of their limited training samples and thus cannot beautify freely drawn sketches with rich variations. To address this challenge, we adopt a divide-and-combine strategy. Specifically, we first parse an input sketch into semantic components, beautify individual components by a learned part beautification module based on part-level implicit manifolds, and then reassemble the beautified components through a structure beautification module. With this strategy, our method can go beyond the training samples and handle novel freehand sketches. We demonstrate the effectiveness of our system with extensive experiments and a perceptive study.