Sketch-based Normal Map Generation with Geometric Sampling
This addresses the need for efficient normal map generation in 3D design, though it appears incremental as it builds on existing GAN and U-Net methods.
The paper tackles the problem of generating normal maps from freehand sketches for 3D content creation, proposing a deep generative model that uses geometric sampling to reduce ambiguity and achieves more accurate results.
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.