Optimal INR freeze depth matches highest weight stable rank layer; SAEs reveal SIREN atoms are localized while FFMLP atoms trace cohort contours with causal impact on PSNR.
Implicit neural video compression
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
NeRC³ applies implicit neural representations with two MLPs to compress static and dynamic point clouds, claiming better rate-distortion than G-PCC/V-PCC standards.
NVRC++ introduces a scalable INR video codec with four complexity levels spanning wide bitrates, real-time decoding, and up to 7.6x faster speed than NVRC at comparable quality.
citing papers explorer
-
What Cohort INRs Encode and Where to Freeze Them
Optimal INR freeze depth matches highest weight stable rank layer; SAEs reveal SIREN atoms are localized while FFMLP atoms trace cohort contours with causal impact on PSNR.
-
Implicit Neural Compression of Point Clouds
NeRC³ applies implicit neural representations with two MLPs to compress static and dynamic point clouds, claiming better rate-distortion than G-PCC/V-PCC standards.
-
Enhanced Neural Video Representation Compression across Extreme Complexity and Quality Scales
NVRC++ introduces a scalable INR video codec with four complexity levels spanning wide bitrates, real-time decoding, and up to 7.6x faster speed than NVRC at comparable quality.