By conditioning video tokenization on an unquantized reference frame, RefTok reports substantially better reconstruction and generation quality than existing tokenizers at claimed equal compression.
Stable video diffusion: Scaling latent video diffusion models to large datasets, 2023
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
-
RefTok: Reference-Based Tokenization for Video Generation
By conditioning video tokenization on an unquantized reference frame, RefTok reports substantially better reconstruction and generation quality than existing tokenizers at claimed equal compression.