EventDiff reports state-of-the-art event-based video frame interpolation by running a latent diffusion denoising process on an event-frame hybrid autoencoder, with only 5 inference steps.
Many-to-many splatting for efficient video frame interpolation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
EventDiff: A Unified and Efficient Diffusion Model Framework for Event-based Video Frame Interpolation
EventDiff reports state-of-the-art event-based video frame interpolation by running a latent diffusion denoising process on an event-frame hybrid autoencoder, with only 5 inference steps.