GSVC represents and compresses video frames as collections of 2D Gaussian splats, using frame prediction, splat pruning and augmentation, and dynamic key-frame selection to match mainstream codec quality with fast decoding.
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
CONDITIONAL 1representative citing papers
citing papers explorer
-
GSVC: Efficient Video Representation and Compression Through 2D Gaussian Splatting
GSVC represents and compresses video frames as collections of 2D Gaussian splats, using frame prediction, splat pruning and augmentation, and dynamic key-frame selection to match mainstream codec quality with fast decoding.