Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models
By Yixin Liu, Kai Zhang, Yuan Li, Zhiling Yan, Chujie Gao, Ruoxi Chen, Zhengqing Yuan, Yue Huang, Hanchi Sun, Jianfeng Gao and 2 more. arXiv.org, 2024
683 citations recorded by the source corpus.
Sora is a text-to-video generative AI model, released by OpenAI in February 2024. The model is trained to generate videos of realistic or imaginative scenes from text instructions and show potential in simulating the physical world. Based on public technical reports and reverse engineering, this paper presents a comprehensive review of the model's background, related technologies, applications, remaining challenges, and future directions of text-to-video AI models. We first trace Sora's development and investigate the underlying technologies used to build this"world simulator". Then, we describe in detail the applications and potential impact of Sora in multiple industries ranging from film-making and education to marketing. We discuss the main challenges and limitations that need to be addressed to widely deploy Sora, such as ensuring safe and unbiased video generation. Lastly, we discuss the future development of Sora and video generation models in general, and how advancements in the field could enable new ways of human-AI interaction, boosting productivity and creativity of video generation.
Subfields: Geology, Ocean Engineering
View Paper: https://www.semanticscholar.org/paper/a6f7485dfdf45320e82d84bcfdc51bcd52dff18b
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Geology
Citations in the corpus
- ShareGPT4Video: Improving Video Understanding and Generation with Better Captions (2024, methodology): “A milestone in this field is Sora [39], which ambitiously employs DiT to train a text-to-video model from scratch.”
- Large Language Models for Education: A survey and outlook (2024, neutral): “Teaching aide gotFeedback gotFeedback was developed to assist teachers in providing more personalized and timely feedback to their students, seamlessly integrating into the gotLearning platform.”
- A Survey on Deep Neural Network Pruning: Taxonomy, Comparison, Analysis, and Recommendations (2023, neutral): “O VER the past several years, Deep Neural Networks ( DNNs ) have achieved conspicuous progress in various domains and applications, such as Computer Vision ( CV ) [1], [2], Natural Language Processing ( NLP ) [3], [4], Audio Signal Processing ( ASP ) [5], [6], and cross-modal applications [7], [8].”