Key points
- Empirical study constructing an animation practice teaching path that integrates generative AI with a Transformer-based human pose estimation model.
- The optimised pose estimation model reduced error to 0.15 and lifted animation generation quality scores to 92 points.
- The AI-integrated teaching group significantly outperformed the traditional group on both technical application and artistic creation indicators.
Summary
This empirical study from Jilin Animation Institute, published in Discover Artificial Intelligence (Springer Nature, Vol. 6, article 315) on 5 March 2026, constructs and tests a practical teaching path integrating generative AI with a Transformer-based human pose estimation model for animation majors. Measured outcomes show the AI-integrated teaching group outperforming traditional instruction on both technical and artistic creation indicators. The study is one of very few empirical, animation-specific pedagogy papers in the literature and is admitted on that basis despite the Discover journal series being relatively young.
Related items
- Analysis of Generative AI for Innovative Thinking in Animation Teaching
- Integrating generative AI in higher art education: a systematic review
Source
Source: Discover Artificial Intelligence (Springer Nature) ↗ (Research)
Cite this item
Zhang, J. & Guan, X. (2026). ‘Path of practical teaching of AI technology in animation majors’, Discover Artificial Intelligence (Springer Nature). Available at: https://link.springer.com/article/10.1007/s44163-026-01036-2
Your reference manager can also read this page directly: with the Zotero (or Mendeley) browser connector installed, save it straight to your library. Whole-collection exports: RIS, BibTeX, CSL-JSON.