FreeSpec uses SVD-based spectral reconstruction to fuse global low-rank and local high-rank features, reducing content drift and preserving temporal dynamics in long video generation.
Freelong: Training-free long video generation with spectralblend temporal attention.Advances in Neural Information Processing Systems, 37: 131434–131455
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
-
FreeSpec: Training-Free Long Video Generation via Singular-Spectrum Reconstruction
FreeSpec uses SVD-based spectral reconstruction to fuse global low-rank and local high-rank features, reducing content drift and preserving temporal dynamics in long video generation.