Results 1 to 10 of about 1,782 (304)

MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators [PDF]

open access: yesarXiv
Recent advances in Text-to-Video generation (T2V) have achieved remarkable success in synthesizing high-quality general videos from textual descriptions. A largely overlooked problem in T2V is that existing models have not adequately encoded physical knowledge of the real world, thus generated videos tend to have limited motion and poor variations.
arxiv  

Home - About - Disclaimer - Privacy