Training-free Slepian acceleration guidance plus structured AR noise improves temporal quality on chunk-wise autoregressive video diffusion without retraining.
Advances in neural information processing systems34, 8780–8794 (2021) 4
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
AVSR-Diff uses a decoupled diffusion framework with TGFR and SAFR modules to deliver temporally consistent arbitrary-scale video super-resolution that outperforms fixed-scale and arbitrary-scale baselines.
citing papers explorer
-
SAGA: Stable Acceleration Guidance for Autoregressive Video Generation
Training-free Slepian acceleration guidance plus structured AR noise improves temporal quality on chunk-wise autoregressive video diffusion without retraining.
-
AVSR-Diff: Scale-Agnostic Diffusion Priors for Temporally Consistent Arbitrary-Scale Video Super-Resolution
AVSR-Diff uses a decoupled diffusion framework with TGFR and SAFR modules to deliver temporally consistent arbitrary-scale video super-resolution that outperforms fixed-scale and arbitrary-scale baselines.