SkelEM decouples skeleton topology from diffusion refinement via disjoint objectives and cycle-consistent alignment on sparse slices to enable fast, high-fidelity self-supervised axial super-resolution with a new BRAVE-ASR benchmark.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SkelEM: Training-Signal Decoupling of Skeleton and Diffusion for Self-supervised Axial Super-Resolution in Volume Microscopy
SkelEM decouples skeleton topology from diffusion refinement via disjoint objectives and cycle-consistent alignment on sparse slices to enable fast, high-fidelity self-supervised axial super-resolution with a new BRAVE-ASR benchmark.