Applications and Limitations of Machine Learning in Computer Graphics
- DOI
- 10.2991/978-94-6463-370-2_55How to use a DOI?
- Keywords
- Computer graphics; Machine learning; Rendering; Modelling; Animation
- Abstract
Just as in many other fields, the application of machine learning methods has become a prominent topic in the realm of computer graphics. This paper reviews and summarizes some ongoing applications of machine learning in both the academic and industrial aspects of computer graphics, along with certain challenges and limitations being faced. The applications encompass the three primary facets of computer graphics: rendering, modelling, and animation. Machine learning’s roles in areas such as anti-aliasing, ambient occlusion, model generation, and motion capture techniques are discussed and also compared with the traditional methods. On the one hand, the advantages of machine learning are shown by the applications part. On the other hand, limitations are also introduced. The limitations section primarily highlights the need for labelled data and associated cost concerns, as well as the inflexibility and lack of creativity inherent to machine learning. In the end, the article provides a summary of the entire content and offers a glimpse into future trends.
- Copyright
- © 2024 The Author(s)
- Open Access
- Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.
Cite this article
TY - CONF AU - Chengyu Fu PY - 2024 DA - 2024/02/14 TI - Applications and Limitations of Machine Learning in Computer Graphics BT - Proceedings of the 2023 International Conference on Data Science, Advanced Algorithm and Intelligent Computing (DAI 2023) PB - Atlantis Press SP - 552 EP - 558 SN - 1951-6851 UR - https://doi.org/10.2991/978-94-6463-370-2_55 DO - 10.2991/978-94-6463-370-2_55 ID - Fu2024 ER -