<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>The development of artificial intelligence technology has become an important trend today and also provides rich means for the development of the animation industry. In this paper, a three-dimensional skeleton extraction model is first proposed through skeletal coordinate transformation, and then a skin deformation technique based on LBS linear hybrid skinning technology is introduced to complete the construction of the character animation generation algorithm. On this basis, a statistical-based scene layout template generation algorithm is proposed to extract spatial relationships in the corpus using the spatial semantic information extraction method and calculate the occurrence probability of objects so as to realize the generation of animated scenes. The PSNR and SSIM scores of the new model have improved by 6.3 and 0.53 points, respectively, when compared to the old model. The recognition accuracy of the latest model reaches 99.6% at a 15° rotation angle and 97.9% at a 30° rotation angle. The average score of the audience for the AIGC-enabled animation scenes is 7.5, which is satisfactory in general. The AIGC-enabled animation character characterization and narrative scene generation have been found to have acceptable results.</p>
</abstract>

The development of artificial intelligence technology has become an important trend today and also provides rich means for the development of the animation industry. In this paper, a three-dimensional skeleton extraction model is first proposed through skeletal coordinate transformation, and then a skin deformation technique based on LBS linear hybrid skinning technology is introduced to complete the construction of the character animation generation algorithm. On this basis, a statistical-based scene layout template generation algorithm is proposed to extract spatial relationships in the corpus using the spatial semantic information extraction method and calculate the occurrence probability of objects so as to realize the generation of animated scenes. The PSNR and SSIM scores of the new model have improved by 6.3 and 0.53 points, respectively, when compared to the old model. The recognition accuracy of the latest model reaches 99.6% at a 15° rotation angle and 97.9% at a 30° rotation angle. The average score of the audience for the AIGC-enabled animation scenes is 7.5, which is satisfactory in general. The AIGC-enabled animation character characterization and narrative scene generation have been found to have acceptable results.

A Study of Characterization and Scene Interaction Narratives of Animated Characters Empowered by AIGC

Communication University of China Nanjing

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

The development of artificial intelligence technology has become an important trend today and also provides rich means for the development of the animation...

A Study of Characterization and Scene Interaction Narratives of Animated Characters Empowered by AIGC

Pubblicato online: 05 ago 2024

Pagine: -

Ricevuto: 02 apr 2024

Accettato: 01 lug 2024

DOI: https://doi.org/10.2478/amns-2024-1918

Parole chiave
AIGC, Skeleton model, Skin deformation, LBS, Scene layout, Animated character

© 2024 Lili Yan, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

A Study of Characterization and Scene Interaction Narratives of Animated Characters Empowered by AIGC

Pubblicato online: 05 ago 2024

Pagine: -

Ricevuto: 02 apr 2024

Accettato: 01 lug 2024

DOI: https://doi.org/10.2478/amns-2024-1918

Parole chiaveAIGC, Skeleton model, Skin deformation, LBS, Scene layout, Animated character

© 2024 Lili Yan, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Parole chiave
AIGC, Skeleton model, Skin deformation, LBS, Scene layout, Animated character