Centroids of many diffusion latents degenerate because small common channel-wise mean biases are amplified by roughly sqrt(N); subtracting each channel's mean before interpolation and adding it back after largely fixes the problem.
In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition
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
-
Addressing degeneracies in latent interpolation for diffusion models
Centroids of many diffusion latents degenerate because small common channel-wise mean biases are amplified by roughly sqrt(N); subtracting each channel's mean before interpolation and adding it back after largely fixes the problem.