Deep Normal Estimation for Automatic Shading of Hand-Drawn Characters

Hudon, Matis; Grogan, Mairéad; Pagés, Rafael; Smolić, Aljoša

doi:10.1007/978-3-030-11015-4_20

Cited by 21 publications

(25 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, we would like to implement a coarse-fine network structure to deal with higher resolution generation and generate normal maps for complex sketches. In addition, we think that the idea of multi-scale processing of the input sketch [7] may be helpful to achieve higher quality normal maps generation. In this work, we integrated the U-Net architecture into the discriminator for more accurate results, this approach may be improved to achieve better generation results.…”

Section: Discussionmentioning

confidence: 99%

Sketch-based normal map generation with geometric sampling

Xie

Zhang

et al. 2021

International Workshop on Advanced Imaging Technology (IWAIT) 2021

View full text Add to dashboard Cite

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.

show abstract

Section: Discussionmentioning

confidence: 99%

Sketch-based normal map generation with geometric sampling

Xie

Zhang

et al. 2021

International Workshop on Advanced Imaging Technology (IWAIT) 2021

View full text Add to dashboard Cite

show abstract

“…Su et al [SDY*18] propose a Generative Adversarial Network to interactively predict surface normals from sketch input. A similar work is presented in [HGPS18] that estimates normal maps from handdrawn characters. Li et al [LPL*18] propose a more generalized solution to model 3D shapes from 2D sketches.…”

Section: Related Workmentioning

confidence: 99%

Neural Modelling of Flower Bas‐relief from 2D Line Drawing

Zhang

Wang

et al. 2021

Computer Graphics Forum

View full text Add to dashboard Cite

Different from other types of bas-reliefs, a flower bas-relief contains a large number of depth-discontinuity edges. Most existing line-based methods reconstruct free-form surfaces by ignoring the depth-discontinuities, thus are less efficient in modeling flower bas-reliefs. This paper presents a neural-based solution which benefits from the recent advances in CNN. Specially, we use line gradients to encode the depth orderings at leaf edges. Given a line drawing, a heuristic method is first proposed to compute 2D gradients at lines. Line gradients and dense curvatures interpolated from sparse user inputs are then fed into a neural network, which outputs depths and normals of the final bas-relief. In addition, we introduce an object-based method to generate flower basreliefs and line drawings for network training. Extensive experiments show that our method is effective in modelling bas-reliefs with depth-discontinuity edges. User evaluation also shows that our method is intuitive and accessible to common users.

show abstract

“…Alternatives include some attempts to base illustration on machine learning [13], [14], [15], and [16]. Different from ours, their target is learning for lighting effects or shadowing, not colorization.…”

Section: Illustration Colorizationmentioning

confidence: 99%

Painting Style-Aware Manga Colorization Based On Generative Adversarial Networks

Shimizu

Furuta

Ouyang

et al. 2021

2021 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

Japanese comics (called manga) are traditionally created in monochrome format. In recent years, in addition to monochrome comics, full color comics, a more attractive medium, have appeared. Unfortunately, color comics require manual colorization, which incurs high labor costs. Although automatic colorization methods have been recently proposed, most of them are designed for illustrations, not for comics. Unlike illustrations, since comics are composed of many consecutive images, the painting style must be consistent.To realize consistent colorization, we propose here a semi-automatic colorization method based on generative adversarial networks (GAN); the method learns the painting style of a specific comic from small amount of training data. The proposed method takes a pair of a screen tone image and a flat colored image as input, and outputs a colorized image. Experiments show that the proposed method achieves better performance than the existing alternatives.

show abstract

Deep Normal Estimation for Automatic Shading of Hand-Drawn Characters

Cited by 21 publications

References 45 publications

Sketch-based normal map generation with geometric sampling

Sketch-based normal map generation with geometric sampling

Neural Modelling of Flower Bas‐relief from 2D Line Drawing

Painting Style-Aware Manga Colorization Based On Generative Adversarial Networks

Contact Info

Product

Resources

About