南洋理工发布了一个AI视频放大算法Upscale-A-Video
Upscale-A-Video的文本引导潜在扩散框架,用于视频放大。该框架通过两个关键机制确保时间上的一致性:在局部上,它将时间层集成到U-Net和VAE-Decoder中,保持短序列的一致性;
https://www.tarogoing.uk/2024/01/05/%e5%8d%97%e6%b4%8b%e7%90%86%e5%b7%a5%e5%8f%91%e5%b8%83%e4%ba%86%e4%b8%80%e4%b8%aaai%e8%a7%86%e9%a2%91%e6%94%be%e5%a4%a7%e7%ae%97%e6%b3%95upscale-a-video/
CleverLibre Social is an inclusive social instance for open discussion, learning, and community. All cultures welcome. Hate speech and harassment strictly forbidden.