UniE2F conditions a pre-trained video diffusion model on event streams with inter-frame residual guidance to reconstruct, interpolate, and predict frames in a unified zero-shot framework.
Advances in Neural Information Processing Systems35, 23593–23606 (2022)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
UniE2F: A Unified Diffusion Framework for Event-to-Frame Reconstruction with Video Foundation Models
UniE2F conditions a pre-trained video diffusion model on event streams with inter-frame residual guidance to reconstruct, interpolate, and predict frames in a unified zero-shot framework.