Research map / 3D vision / Face and shape
Recover Biological Structure from Sparse-View Diffraction Images with Neural Volumetric Prior
Renzhi He, Haowen Zhou, Yubei Chen, Yi Xue
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 |
|---|---|---|---|
| use NVP hybrid explicit-plus-MLP representation instead of explicit grid | NVP · Synthetic cells RI (6 illuminations) | PSNR: 28.6203 -> 30.7318 | Improved |
| use NVP instead of triplane representation | NVP · Synthetic cells RI (6 illuminations) | SSIM: 0.7128 -> 0.8910 | Improved |
| reduce number of fluorescence images from 20 to 6 (ablation) | NVP · Synthetic cells RI | PSNR: only a 0.65 decrease in PSNR and a 0.005 decrease in SSIM | No clear effect |
| use NVP instead of explicit method on synthetic tissue | NVP · Synthetic tissue RI (7 illuminations) | SSIM: 0.2954 -> 0.4775 | Improved |
| use NVP instead of triplane on synthetic tissue | NVP · Synthetic tissue RI (7 illuminations) | PSNR: 9.0632 -> 11.6412 | Improved |
| use NVP instead of explicit method on real MDCK cells | NVP · Real MDCK cells predicted images (19 images) | PSNR: 36.6540 -> 40.7043 | Improved |
| use NVP instead of triplane on real MDCK cells | NVP · Real MDCK cells predicted images (19 images) | LPIPS: 0.0285 -> 0.0015 | Improved |
| use NVP instead of explicit baseline for convergence | NVP · Real MDCK cells | time to SSIM>0.99: 60 minutes -> 20 minutes | Improved |
| use triplane instead of explicit method on synthetic cells with 6 illuminations | Triplane · Synthetic cells RI (6 illuminations) | SSIM: 0.8540 -> 0.7128 | Hurt |
| increase illuminations from 6 to 20 for triplane (ablation) | Triplane · Synthetic cells RI | SSIM: 0.7128 -> 0.9621 | Improved |
Closest papers by meaning
- MicroDiffusion: Implicit Representation-Guided Diffusion for 3D Reconstruction from Limited 2D Microscopy Projections (CVPR 2024 · similarity 0.87)
- Volume Tells: Dual Cycle-Consistent Diffusion for 3D Fluorescence Microscopy De-noising and Super-Resolution (CVPR 2025 · similarity 0.86)
- From Pixels to Views: Learning Angular-Aware and Physics-Consistent Representations for Light Field Microscopy (NeurIPS 2025 · similarity 0.86)
- V2V3D: View-to-View Denoised 3D Reconstruction for Light Field Microscopy (CVPR 2025 · similarity 0.85)
- Light Transport-aware Diffusion Posterior Sampling for Single-View Reconstruction of 3D Volumes (CVPR 2025 · similarity 0.85)
- 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.
