A latent diffusion model conditioned on keyframe latents reconstructs non-key frames, giving higher compression ratios than prior scientific data compressors.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Generative Latent Diffusion for Efficient Spatiotemporal Data Reduction
A latent diffusion model conditioned on keyframe latents reconstructs non-key frames, giving higher compression ratios than prior scientific data compressors.