Under equal training time, a recombined NeRV architecture (RNeRV) beats prior NeRV variants on UVG, and weight token masking lets hyper-network codecs trade bitrate for quality.
Scale-space flow for end-to-end optimized video com- pression
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
-
How to Design and Train Your Implicit Neural Representation for Video Compression
Under equal training time, a recombined NeRV architecture (RNeRV) beats prior NeRV variants on UVG, and weight token masking lets hyper-network codecs trade bitrate for quality.