Bootstrapping diffusion trains per-view diffusion models on partial data and a residual denoiser on a small full-resolution set, claiming provable near-optimal data efficiency that the paper does not actually prove.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data
Bootstrapping diffusion trains per-view diffusion models on partial data and a residual denoiser on a small full-resolution set, claiming provable near-optimal data efficiency that the paper does not actually prove.