Sketch-based Normal Map Generation with Geometric Sampling

TL;DR

This paper introduces a deep generative model that creates accurate normal maps from sketches using geometric sampling and a conditional GAN, enhancing 3D content creation workflows.

Contribution

It presents a novel framework combining geometric sampling with a conditional GAN and U-Net discriminator for improved normal map generation from sketches.

Findings

Generated normal maps are more accurate.

The method reduces ambiguity in generation results.

Framework outperforms existing approaches.

Abstract

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.