LIPAR prunes redundant inter-frame latent patches in video generation and recovers attention to deliver 1.53x speedup at 19.3 FPS with no quality drop or extra training.
CVPR Workshop on Efficient Deep Learning for Computer Vision (2023)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Video Compression Meets Video Generation: Latent Inter-Frame Pruning with Attention Recovery
LIPAR prunes redundant inter-frame latent patches in video generation and recovers attention to deliver 1.53x speedup at 19.3 FPS with no quality drop or extra training.