# Sketch-based Normal Map Generation with Geometric Sampling

arXiv: https://arxiv.org/abs/2104.11554 · HTML: https://mlsanity.com/paper/2104.11554/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 18 references that are in the map.
- First posted on arXiv 23 Apr 2021.

## Builds on (most cited first, 10 of 10)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [Wasserstein GAN](https://mlsanity.com/paper/1701.07875/) (2017)
- [Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture](https://mlsanity.com/paper/1411.4734/) (2014)
- [A U-Net Based Discriminator for Generative Adversarial Networks](https://mlsanity.com/paper/2002.12655/) (2020)
- [Designing Deep Networks for Surface Normal Estimation](https://mlsanity.com/paper/1411.4958/) (2014)
- [3D Shape Reconstruction from Sketches via Multi-view Convolutional Networks](https://mlsanity.com/paper/1707.06375/) (2017)
- [DeepSketch2Face: A Deep Learning Based Sketching System for 3D Face and Caricature Modeling](https://mlsanity.com/paper/1706.02042/) (2017)

## Built on by (most cited first, 3 of 3)

- [dualFace:Two-Stage Drawing Guidance for Freehand Portrait Sketching](https://mlsanity.com/paper/2104.12297/) (2021)
- [Sketch2Cloth: Sketch-based 3D Garment Generation with Unsigned Distance Fields](https://mlsanity.com/paper/2303.00167/) (2023)
- [Interactive 3D Character Modeling from 2D Orthogonal Drawings with Annotations](https://mlsanity.com/paper/2201.11284/) (2022)

## Abstract (arXiv)

Normal map is an important and efficient way to represent complex 3D models. A designer may benefit from the auto-generation of high quality and accurate normal maps from freehand sketches in 3D content creation. This paper proposes a deep generative model for generating normal maps from users sketch with geometric sampling. Our generative model is based on Conditional Generative Adversarial Network with the curvature-sensitive points sampling of conditional masks. This sampling process can help eliminate the ambiguity of generation results as network input. In addition, we adopted a U-Net structure discriminator to help the generator be better trained. It is verified that the proposed framework can generate more accurate normal maps.