3 papers
cs.CV2024
I4VGen: Image as Free Stepping Stone for Text-to-Video Generation
Xiefan Guo, Jinlin Liu, Miaomiao Cui +2
Text-to-video generation has trailed behind text-to-image generation in terms of quality and diversity, primarily due to the inherent complexities of spatio-temporal modeling and t…
cs.CV2024
Disentangling Foreground and Background Motion for Enhanced Realism in Human Video Generation
Jinlin Liu, Kai Yu, Mengyang Feng +2
Recent advancements in human video synthesis have enabled the generation of high-quality videos through the application of stable diffusion models. However, existing methods predom…
cs.CV2024
InitNO: Boosting Text-to-Image Diffusion Models via Initial Noise Optimization
Xiefan Guo, Jinlin Liu, Miaomiao Cui +3
Recent strides in the development of diffusion models, exemplified by advancements such as Stable Diffusion, have underscored their remarkable prowess in generating visually compel…