Research map / 3D vision / Face and shape
VEMamba: Efficient Isotropic Reconstruction of Volume Electron Microscopy with Axial-Lateral Consistent Mamba
Longmi Gao, Pan Gao
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add ALCSSM instead of baseline continuous scan (ablation) | VEMamba · EPFL x4 | PSNR: 29.372 -> 29.442 | Improved |
| add DWAM instead of simple feature summation (ablation) | VEMamba · EPFL x4 | PSNR: 29.381 -> 29.442 | Improved |
| add MoCo-based degradation learning (ablation) | VEMamba · EPFL x4 | PSNR: 29.396 -> 29.442 | Improved |
| use VEMamba instead of IsoVEM | isotropic VEM reconstruction · CREMI x4 | PSNR: 37.807 -> 37.785 | No clear effect |
| use VEMamba instead of IsoVEM | isotropic VEM reconstruction · EPFL x8 | PSNR: 27.119 -> 27.418 | Improved |
| use VEMamba instead of EMDiffuse in LPIPS terms | isotropic VEM reconstruction · CREMI x4 | LPIPS: 0.1362 -> 0.2021 | Hurt |
| use VEMamba instead of IsoVEM | mitochondria segmentation · EPFL x4 | IoU: 0.7351 -> 0.7464 | Improved |
| use VEMamba instead of EMDiffuse (compute) | isotropic VEM reconstruction · Compute cost | FLOPs (T): 22.51 -> 0.28 | Improved |
Closest papers by meaning
- A Gaussian Filter-Based 3D Registration Method for Series Section Electron Microscopy (AAAI 2025 · similarity 0.85)
- Volume Tells: Dual Cycle-Consistent Diffusion for 3D Fluorescence Microscopy De-noising and Super-Resolution (CVPR 2025 · similarity 0.84)
- From Pixels to Views: Learning Angular-Aware and Physics-Consistent Representations for Light Field Microscopy (NeurIPS 2025 · similarity 0.84)
- At FullTilt: Real-Time Open-Set 3D Macromolecule Detection Directly from Tilted 2D Projections (NeurIPS 2026 · similarity 0.84)
- MicroDiffusion: Implicit Representation-Guided Diffusion for 3D Reconstruction from Limited 2D Microscopy Projections (CVPR 2024 · similarity 0.84)
- CD-RCM: Generalizable Continuous-Depth Novel View Synthesis for Reflectance Confocal Microscopy (NeurIPS 2026 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
