# SkelEM: Training-Signal Decoupling of Skeleton and Diffusion for Self-supervised Axial Super-Resolution in Volume Microscopy

arXiv: https://arxiv.org/abs/2606.30012 · HTML: https://mlsanity.com/paper/2606.30012/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 52 references that are in the map.
- First posted on arXiv 29 Jun 2026.

## Builds on (most cited first, 23 of 23)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [The Perception-Distortion Tradeoff](https://mlsanity.com/paper/1711.06077/) (2017)
- [Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation](https://mlsanity.com/paper/1712.00080/) (2017)
- [Real-Time Intermediate Flow Estimation for Video Frame Interpolation](https://mlsanity.com/paper/2011.06294/) (2020)
- [IoU Loss for 2D/3D Object Detection](https://mlsanity.com/paper/1908.03851/) (2019)
- [Arbitrary-steps Image Super-resolution via Diffusion Inversion](https://mlsanity.com/paper/2412.09013/) (2024)
- [Video Interpolation with Diffusion Models](https://mlsanity.com/paper/2404.01203/) (2024)
- [Improving 3D Imaging with Pre-Trained Perpendicular 2D Diffusion Models](https://mlsanity.com/paper/2303.08440/) (2023)
- [Enhanced Quadratic Video Interpolation](https://mlsanity.com/paper/2009.04642/) (2020)
- [Isotropic reconstruction of 3D fluorescence microscopy images using convolutional neural networks](https://mlsanity.com/paper/1704.01510/) (2017)
- [Deep Learning for Isotropic Super-Resolution from Non-Isotropic 3D Electron Microscopy](https://mlsanity.com/paper/1706.03142/) (2017)
- [DiffuseIR:Diffusion Models For Isotropic Reconstruction of 3D Microscopic Images](https://mlsanity.com/paper/2306.12109/) (2023)
- [Deep learning enables reference-free isotropic super-resolution for volumetric fluorescence microscopy](https://mlsanity.com/paper/2104.09435/) (2021)
- [Hierarchical Flow Diffusion for Efficient Frame Interpolation](https://mlsanity.com/paper/2504.00380/) (2025)
- [Reference-Free Isotropic 3D EM Reconstruction using Diffusion Models](https://mlsanity.com/paper/2308.01594/) (2023)
- [Learning Multimodal Volumetric Features for Large-Scale Neuron Tracing](https://mlsanity.com/paper/2401.03043/) (2024)
- [Super-resolution of biomedical volumes with 2D supervision](https://mlsanity.com/paper/2404.09425/) (2024)
- [Reference-free Axial Super-resolution of 3D Microscopy Images using Implicit Neural Representation with a 2D Diffusion Prior](https://mlsanity.com/paper/2408.08616/) (2024)
- [Removing Stripes, Scratches, and Curtaining with Non-Recoverable Compressed Sensing](https://mlsanity.com/paper/1901.08001/) (2019)

## Abstract (arXiv)

Volume microscopy, including electron and light microscopy, suffers from severe anisotropic resolution due to physical axial sectioning. Existing self-supervised axial super-resolution (ASR) methods face a trilemma bounded by overly smoothed regression textures, structural hallucinations of pure diffusion models, and prohibitive inference latency. In this paper, we propose Skeleton-refinE Microscopy (SkelEM), a self-supervised framework that decouples ASR at the training-signal level: a frozen topological network and a diffusion refiner are optimized by disjoint objectives, separating low-frequency topology formulation from high-frequency detail enhancement. Building on this deterministic skeleton, we exploit a unified cycle-consistent mechanism on input sparse slices to simultaneously extract a real-domain residual prior and bidirectionally align the diffusion refiner, washing away cross-plane artifacts without synthetic bias. By truncating the reverse diffusion process with this physical prior, SkelEM achieves high-fidelity detail restoration in merely ≤ 5 steps. To rigorously assess cross-instrument generalization, we further introduce BRAVE-ASR, a new benchmark of co-aligned anisotropic and isotropic volumes acquired on a Plasma-FIB instrument. Across public benchmarks, SkelEM achieves the most favorable balance across the fidelity-perception trade-off among self-supervised methods, with state-of-the-art downstream membrane segmentation performance and robust zero-shot generalization across distinct modalities.