ERank in Latent Space as an Image-Complexity and Richness Measure
We propose the effective rank (ERank) of the channel covariance of an image's deep feature map as a per-sample, label-free measure of visual richness, computed from a single forward pass through a frozen pretrained encoder. ERank counts how many decorrelated channel directions an image activates, and we characterize its properties, including its behavior under noise. Empirically, ERank orders images from plain to visually rich, correlates with codec bitrate, sharpness, and edge density, and correlates with human complexity annotations on IC9600 with $r = 0.72$. As a data-selection criterion, r
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 59%Tongyi-MAI/Z-Image-Turbo →
“Fuzzy title match (0.73): “ERank in Latent Space as an Image-Complexity and Richness Me” ≈ “Tongyi-MAI/Z-Image-Turbo””
- LinkedLinked via arxiv author · 85%Maksim Smirnov →
“ERank in Latent Space as an Image-Complexity and Richness Measure”
- LinkedLinked via arxiv author · 85%Grigory Kononov →
“ERank in Latent Space as an Image-Complexity and Richness Measure”
- LinkedLinked via arxiv author · 85%Anastasiia Linich →
“ERank in Latent Space as an Image-Complexity and Richness Measure”
- LinkedLinked via arxiv author · 85%Egor Surkov →
“ERank in Latent Space as an Image-Complexity and Richness Measure”
- LinkedLinked via arxiv author · 85%Egor Shvetsov →
“ERank in Latent Space as an Image-Complexity and Richness Measure”