scholarly journals Line Drawing Extraction from Cartoons Using a Conditional Generative Adversarial Network

2021 ◽  
Vol 11 (16) ◽  
pp. 7536
Author(s):  
Kyungho Yu ◽  
Juhyeon Noh ◽  
Hee-Deok Yang
Keyword(s):  
3D Model ◽  
Line Drawing ◽  
Three Dimensional ◽  
Generative Adversarial Network ◽  
Line Drawings ◽  
Geometric Characteristics ◽  
Adversarial Network ◽  
Time Required ◽  
3D Information ◽  
3D Content

Recently, three-dimensional (3D) content used in various fields has attracted attention owing to the development of virtual reality and augmented reality technologies. To produce 3D content, we need to model the objects as vertices. However, high-quality modeling is time-consuming and costly. Drawing-based modeling is a technique that shortens the time required for modeling. It refers to creating a 3D model based on a user’s line drawing, which is a 3D feature represented by two-dimensional (2D) lines. The extracted line drawing provides information about a 3D model in the 2D space. It is sometimes necessary to generate a line drawing from a 2D cartoon image to represent the 3D information of a 2D cartoon image. The extraction of consistent line drawings from 2D cartoons is difficult because the styles and techniques differ depending on the designer who produces the 2D cartoons. Therefore, it is necessary to extract line drawings that show the geometric characteristics well in 2D cartoon shapes of various styles. This paper proposes a method for automatically extracting line drawings. The 2D cartoon shading image and line drawings are learned using a conditional generative adversarial network model, which outputs the line drawings of the cartoon artwork. The experimental results show that the proposed method can obtain line drawings representing the 3D geometric characteristics with a 2D line when a 2D cartoon painting is used as the input.

scholarly journals 3D Model Generation on Architectural Plan and Section Training through Machine Learning

Technologies ◽  
2019 ◽  
Vol 7 (4) ◽  
pp. 82
Author(s):  
Hang Zhang
Keyword(s):  
Machine Learning ◽  
3D Model ◽  
Three Dimensional ◽  
Image Data ◽  
Input Image ◽  
Model Generation ◽  
Three Dimensional Model ◽  
Generative Adversarial Network ◽  
Learning Group ◽  
Adversarial Network

Machine learning, especially the GAN (Generative Adversarial Network) model, has been developed tremendously in recent years. Since the NVIDIA Machine Learning group presented the StyleGAN in December 2018, it has become a new way for designers to make machines learn different or similar types of architectural photos, drawings, and renderings, then generate (a) similar fake images, (b) style-mixing images, and (c) truncation trick images. The author both collected and created input image data, and specially made architectural plan and section drawing inputs with a clear design purpose, then applied StyleGAN to train specific networks on these datasets. With the training process, we could look into the deep relationship between these input architectural plans or sections, then generate serialized transformation images (truncation trick images) to form the 3D (three-dimensional) model with a decent resolution (up to 1024 × 1024 × 1024 pixels). Though the results of the 3D model generation are difficult to use directly in 3D spatial modeling, these unexpected 3D forms still could inspire new design methods and greater possibilities of architectural plan and section design.

scholarly journals 3D-StyleGAN: A Style-Based Generative Adversarial Network for Generative Modeling of Three-Dimensional Medical Images

2021 ◽  
pp. 24-34
Author(s):  
Sungmin Hong ◽  
Razvan Marinescu ◽  
Adrian V. Dalca ◽  
Anna K. Bonkhoff ◽  
Martin Bretzner ◽  
...  
Keyword(s):  
Medical Images ◽  
Three Dimensional ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Generative Modeling

scholarly journals Matching of 3D Model and Semantic Description via Multi-Modal Auxiliary Classifier Generative Adversarial Network With Autoencoder

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 177585-177594
Author(s):  
Long Zhang ◽  
Li Liu ◽  
Huaxiang Zhang ◽  
Xiuxiu Chen ◽  
Tianshi Wang ◽  
...  
Keyword(s):  
3D Model ◽  
Semantic Description ◽  
Generative Adversarial Network ◽  
Adversarial Network

scholarly journals The Use of Gigapixel Photogrammetry for the Understanding of Landslide Processes in Alpine Terrain

Geosciences ◽  
2019 ◽  
Vol 9 (2) ◽  
pp. 99 ◽  
Author(s):  
Saverio Romeo ◽  
Lucio Di Matteo ◽  
Daniel Kieffer ◽  
Grazia Tosi ◽  
Aurelio Stoppini ◽  
...  
Keyword(s):  
3D Model ◽  
Low Cost ◽  
Three Dimensional ◽  
Image Sequences ◽  
Synthetic Aperture ◽  
Synthetic Aperture Radar Interferometry ◽  
Experimental Application ◽  
Single Lens ◽  
Landslide Processes ◽  
3D Information

The work in this paper illustrates an experimental application for geosciences by coupling new and low cost photogrammetric techniques: Gigapixel and Structure-from-Motion (SfM). Gigapixel photography is a digital image composed of billions of pixels (≥1000 megapixels) obtained from a conventional Digital single-lens reflex camera (DSLR), whereas the SfM technique obtains three-dimensional (3D) information from two-dimensional (2D) image sequences. The field test was carried out at the Ingelsberg slope (Bad Hofgastein, Austria), which hosts one of the most dangerous landslides in the Salzburg Land. The stereographic analysis carried out on the preliminary 3D model, integrated with Ground Based Synthetic Aperture Radar Interferometry (GBInSAR) data, allowed us to obtain the main fractures and discontinuities of the unstable rock mass.

scholarly journals Multiautonomous underwater vehicle consistent collaborative hunting method based on generative adversarial network

2020 ◽  
Vol 17 (3) ◽  
pp. 172988142092523
Author(s):  
Lei Cai ◽  
Qiankun Sun
Keyword(s):  
Autonomous Underwater Vehicle ◽  
Kinematic Model ◽  
Three Dimensional ◽  
Laplacian Matrix ◽  
Underwater Vehicle ◽  
Underwater Acoustic Communication ◽  
Constant Modulus Algorithm ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
The Ideal

The time-varying ocean currents and the delay of underwater acoustic communication have caused the uncertainty of single autonomous underwater vehicle (AUV) tracking target and the inconsistency of multi-AUV coordination, which make it difficult for multiple AUVs to form a hunting alliance. To solve the above problems, this article proposes the multi-AUV consistent collaborative hunting method based on generative adversarial network (GAN). Firstly, the three-dimensional (3D) kinematic model of AUV is established for the underwater 3D environment. Secondly, combined with the Laplacian matrix, the topology of the hunting alliance in the ideal environment is established, and the control rate of AUV is calculated. Finally, using the GAN network model, the control relationship after environmental interference is used as the input of the generative model. The control rate in the ideal environment is used as the comparison object of the discriminative model. Using the iterative training of GAN to generate a control rate that adapts to the current interference environment and combining multi-AUV topological hunting model to achieve successful hunting of noncooperative target, the experimental results show that the algorithm reduces the average hunting time to 62.53 s and the success rate of hunting is increased to 84.69%, which is 1.17% higher than the particle swarm optimization-constant modulus algorithm (PSO-CMA) algorithm.

A Machine Learning Application Based On Giorgio Morandi Still Life Paintings To Assist Artists In The Choice Of 3d Compositions

Leonardo ◽  
2021 ◽  
pp. 1-8
Author(s):  
Guido Salimbeni ◽  
Frederic Fol Leymarie ◽  
William Latham
Keyword(s):  
Machine Learning ◽  
Creative Process ◽  
Three Dimensional ◽  
Still Life ◽  
Generative Adversarial Network ◽  
Aesthetic Evaluation ◽  
Adversarial Network ◽  
The Media ◽  
Dimensional Models ◽  
Three Dimensional Models

Abstract We present a system built to generate arrangements of three-dimensional models for aesthetic evaluation, with the aim to support an artist in their creative process. We explore how this system can automatically generate aesthetically pleasing content for use in the media and design industry, based on standards originally developed in master artworks. We demonstrate the effectiveness of our process in the context of paintings using a collection of images inspired by the work of the artist Giorgio Morandi (Bologna, 1890 -- 1964). Finally, we compare the results of our system with the results of a well-known Generative Adversarial Network (GAN).

Research on the Platform of 3D Information Management for the Ordnance Maintenance Equipment

2014 ◽  
Vol 989-994 ◽  
pp. 5427-5430
Author(s):  
Zhi Yong Cheng ◽  
Rong Yue Xie ◽  
Lei Qiu ◽  
Xiao Zhou ◽  
Chao Fa Yu
Keyword(s):  
Information Management ◽  
Management System ◽  
3D Model ◽  
Three Dimensional ◽  
Original Data ◽  
Information Management System ◽  
Equipment Management ◽  
Two Dimensional ◽  
New Information ◽  
3D Information

Based on the current situation that the current ordnance equipment maintenance information management system is not intuitive, a new information system was designed and realized, which could display the two-dimensional Information and three-dimensional information synchronously. This system can well compatible with the existing one. Through studying the analysis of the original data structure, importing way for the 3D model of equipment, synchronous display for the 2D information and 3d model, the 3D information management system was realized, which provides a new digital method for equipment management person.

Sign in / Sign up

Export Citation Format

Share Document