Pixel artifacts in latent SDS are caused by VAE-induced pixel drift, and decoding the latent SDS lookahead provides a clean gradient direction that reduces them.
Understanding Variational Autoencoders with Intrinsic Dimension and Information Imbalance
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
This work presents an analysis of the hidden representations of Variational Autoencoders (VAEs) using the Intrinsic Dimension (ID) and the Information Imbalance (II). We show that VAEs undergo a transition in behaviour once the bottleneck size is larger than the ID of the data, manifesting in a double hunchback ID profile and a qualitative shift in information processing as captured by the II. Our results also highlight two distinct training phases for architectures with sufficiently large bottleneck sizes, consisting of a rapid fit and a slower generalisation, as assessed by a differentiated behaviour of ID, II, and KL loss. These insights demonstrate that II and ID could be valuable tools for aiding architecture search, for diagnosing underfitting in VAEs, and, more broadly, they contribute to advancing a unified understanding of deep generative models through geometric analysis.
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PixSDS: Why Latent SDS Makes Noisy Pixels
Pixel artifacts in latent SDS are caused by VAE-induced pixel drift, and decoding the latent SDS lookahead provides a clean gradient direction that reduces them.