A dictionary-based multi-item codec sparsely projects CLIP image embeddings onto learned semantic atoms and regenerates images with unCLIP, reaching about 1e-4 BPP per image on a 5000-image collection.
Performance of the h. 263 video compression standard,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.IV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
SMIC: Semantic Multi-Item Compression based on CLIP dictionary
A dictionary-based multi-item codec sparsely projects CLIP image embeddings onto learned semantic atoms and regenerates images with unCLIP, reaching about 1e-4 BPP per image on a 5000-image collection.