A ControlNet-style conditional encoder adapts Stable Video Diffusion for large-motion frame interpolation, achieving lower FVD than AMT, FILM, and SVDKFI on DAVIS-7 and UCF101-7.
Video frame interpolation via deformable separable convolution,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Adapting Image-to-Video Diffusion Models for Large-Motion Frame Interpolation
A ControlNet-style conditional encoder adapts Stable Video Diffusion for large-motion frame interpolation, achieving lower FVD than AMT, FILM, and SVDKFI on DAVIS-7 and UCF101-7.