Research map / 3D vision / Gaussian splatting
EMGauss: Continuous Slice-to-3D Reconstruction via Dynamic Gaussian Modeling in Volume Electron Microscopy
Yumeng He, Zanwei Zhou, Yekun Zheng, Chen Liang, Yunbo Wang, Xiaokang Yang
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 the teacher-student pseudo-labeling module (ablation) | EMGauss · EPFL+FIB-25 average | PSNR: 25.19 -> 26.98 | Improved |
| add the teacher-student pseudo-labeling module (ablation) | EMGauss · EPFL+FIB-25 average | SSIM: 0.6272 -> 0.7126 | Improved |
| add the warm-up stage (ablation) | EMGauss · EPFL+FIB-25 average | PSNR: 25.76 -> 26.98 | Improved |
| add the joint training stage (ablation) | EMGauss · EPFL+FIB-25 average | PSNR: 24.35 -> 26.98 | Improved |
| add the joint training stage (ablation) | EMGauss · EPFL+FIB-25 average | FSIM: 0.8513 -> 0.9315 | Improved |
| make opacity dynamic (add Delta o) (ablation) | EMGauss · EPFL+FIB-25 average | PSNR: 25.44 -> 26.98 | Improved |
| remove time-dependent rotation (Delta R) (ablation) | EMGauss · EPFL+FIB-25 average | PSNR: 25.07 -> 26.98 | Improved |
| replace EMDiffuse with EMGauss | vEM slice reconstruction · EPFL (x6) | PSNR: 23.34 -> 26.59 | Improved |
| replace IsoVEM with EMGauss | vEM slice reconstruction · FIB-25 (x6) | PSNR: 21.51 -> 27.37 | Improved |
| replace EMDiffuse with EMGauss reconstruction before SAM2 segmentation | SAM2 video segmentation · EPFL (x6) | IoU: 0.9555 -> 0.9687 | Improved |
Closest papers by meaning
- A Gaussian Filter-Based 3D Registration Method for Series Section Electron Microscopy (AAAI 2025 · similarity 0.87)
- MicroDiffusion: Implicit Representation-Guided Diffusion for 3D Reconstruction from Limited 2D Microscopy Projections (CVPR 2024 · similarity 0.85)
- From Pixels to Views: Learning Angular-Aware and Physics-Consistent Representations for Light Field Microscopy (NeurIPS 2025 · similarity 0.85)
- Learning Large-Factor EM Image Super-Resolution with Generative Priors (CVPR 2024 · similarity 0.85)
- At FullTilt: Real-Time Open-Set 3D Macromolecule Detection Directly from Tilted 2D Projections (NeurIPS 2026 · similarity 0.85)
- Volume Tells: Dual Cycle-Consistent Diffusion for 3D Fluorescence Microscopy De-noising and Super-Resolution (CVPR 2025 · 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.
