Min-Su Yu, Tae-Won Jung, GyoungHyun Kim, Soonchul Kwon, Kye-Dong Jung
언어
영어(ENG)
URL
https://www.earticle.net/Article/A440423
※ 원문제공기관과의 협약기간이 종료되어 열람이 제한될 수 있습니다.
원문정보
초록
영어
We present a method for generating 3D structures and rendering objects by combining VAE (Variational Autoencoder) and GAN (Generative Adversarial Network). This approach focuses on generating and rendering 3D models with improved quality using residual learning as the learning method for the encoder. We deep stack the encoder layers to accurately reflect the features of the image and apply residual blocks to solve the problems of deep layers to improve the encoder performance. This solves the problems of gradient vanishing and exploding, which are problems when constructing a deep neural network, and creates a 3D model of improved quality. To accurately extract image features, we construct deep layers of the encoder model and apply the residual function to learning to model with more detailed information. The generated model has more detailed voxels for more accurate representation, is rendered by adding materials and lighting, and is finally converted into a mesh model. 3D models have excellent visual quality and accuracy, making them useful in various fields such as virtual reality, game development, and metaverse.
목차
Abstract 1. Introduction 2. Proposed Method 2.1 3D Object Generation using ResNet-GAN 2.2 Rendering and Mesh Transformation 3. Experimental 4. Conclusion Acknowledgement References
Min-Su Yu [ Master Student, Department of Smart Convergence, Kwangwoon University, Korea ]
Tae-Won Jung [ Department of Immersive Content Convergence, Kwangwoon University, Korea ]
GyoungHyun Kim [ Master Student, Department of Interdisciplinary Information System, Graduate School of Smart Convergence, Kwangwoon University, Korea ]
Soonchul Kwon [ Associate professor, Department of Interdisciplinary Information System, Graduate School of Smart Convergence, Kwangwoon University, Korea ]
Kye-Dong Jung [ Professor, Ingenium College of Liberal Arts, Kwangwoon University, Korea ]
Corresponding Author