ContentsI. Introduction
In this study, our objective is to generate a video that is consistent in both temporal and spatial aspects based on text input. Additionally, we aim to enhance the diversity of the generated videos to cater to user preferences.
Abstract:
This paper proposes a method to improve the quality of generated videos in text to video generation techniques based on diffusion models, which suffer from low quality an...View moreMetadata
Abstract:
This paper proposes a method to improve the quality of generated videos in text to video generation techniques based on diffusion models, which suffer from low quality and poor continuity.The method involves dynamically adjusting the noise frame connections to enhance the video quality. A Reconstruction Net is introduced to automatically adjust the noise correlation among frames during the training process. Experimental results demonstrate that this method can enhance the quality of generated videos, improve video continuity, enhance the representation of image details, and strengthen the correspondence between generated and original videos. This research is of significant importance in advancing the development of text-based video generation techniques based on diffusion models.
Published in: 2023 2nd International Conference on Computing, Communication, Perception and Quantum Technology (CCPQT)
Date of Conference: 04-07 August 2023
Date Added to IEEE Xplore: 11 December 2023
ISBN Information:
