Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Longquan Yan"'
Publikováno v:
Heritage Science, Vol 12, Iss 1, Pp 1-12 (2024)
Abstract Utilizing Generative Adversarial Networks (GANs) to generate 3D representations of the Terracotta Warriors offers a novel approach for the preservation and restoration of cultural heritage. Through GAN technology, we can produce complete 3D
Externí odkaz:
https://doaj.org/article/2653c412723245fe9c26159a4204cd94
Publikováno v:
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Autor:
Longquan Yan, Wei Shi
Publikováno v:
2022 Data Compression Conference (DCC).
Publikováno v:
2021 5th International Conference on Automation, Control and Robots (ICACR).
Thangka images are rich in content and complex in texture information, so it is difficult to fully extract effective features and achieve good retrieval effect. This paper proposes that the extracted convolutional layer features are hashed with mean