Research map / 3D vision / NeRF and radiance fields
Learning Adaptive Tensorial Density Fields for Clean Cryo-ET Reconstruction
YUANHAO WANG, Ramzi Idoughi, Wolfgang Heidrich
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 |
|---|---|---|---|
| increase tensor dimension from 10 to 22 (ablation) | Adaptive TensorDF · Simulated tomogram | 3D PSNR: 35.86 -> 37.45 | Improved |
| increase tensor dimension from 22 to 30 (ablation) | Adaptive TensorDF · Simulated tomogram | 3D PSNR: 37.45 -> 37.12 | Hurt |
| increase tensor dimension from 22 to 26 (ablation) | Adaptive TensorDF · Simulated tomogram | 3D SSIM: 0.820 -> 0.747 | Hurt |
| increase feature size from 4 to 16 (ablation) | Adaptive TensorDF · Simulated tomogram | 3D PSNR: 37.21 -> 37.86 | Improved |
| increase feature size from 16 to 20 (ablation) | Adaptive TensorDF · Simulated tomogram | 3D SSIM: 0.837 -> 0.822 | Hurt |
| add isotropic Fourier prior to TensoRF (ablation) | TensoRF · EMPIAR 10643-40 | CNR: 0.4123 -> 0.4470 | Improved |
| add isotropic Fourier prior to TensoRF (ablation) | TensoRF · EMPIAR 10643-40 | ENL: 48.293 -> 69.483 | Improved |
| add TV loss to TensoRF (ablation) | TensoRF · EMPIAR 10643-40 | CNR: 0.2884 -> 0.4123 | Improved |
| add TV loss to TensoRF (ablation) | TensoRF · EMPIAR 10643-51 | ENL: 21.120 -> 24.419 | Improved |
| replace global TensoRF planes with quadtree adaptive local tensors plus priors (ablation) | TensoRF with Fourier prior · EMPIAR 10643-40 | CNR: 0.4470 -> 0.6808 | Improved |
| replace global TensoRF planes with quadtree adaptive local tensors plus priors (ablation) | TensoRF with Fourier prior · EMPIAR 10643-51 | ENL: 25.256 -> 66.015 | Improved |
| Adaptive TensorDF versus I-NGP | Adaptive TensorDF · EMPIAR 10643-40 | ENL: 52.231 -> 114.400 | Improved |
Closest papers by meaning
- CryoSPIN: Improving Ab-Initio Cryo-EM Reconstruction with Semi-Amortized Pose Inference (NeurIPS 2024 · similarity 0.87)
- cryoSPHERE: Single-Particle HEterogeneous REconstruction from cryo EM (ICLR 2025 · similarity 0.87)
- Vox-UDA: Voxel-wise Unsupervised Domain Adaptation for Cryo-Electron Subtomogram Segmentation with Denoised Pseudo-Labeling (AAAI 2025 · similarity 0.87)
- BOE-ViT: Boosting Orientation Estimation with Equivariance in Self-Supervised 3D Subtomogram Alignment (CVPR 2025 · similarity 0.86)
- CryoGEM: Physics-Informed Generative Cryo-Electron Microscopy (NeurIPS 2024 · similarity 0.86)
- Reconstructing Heterogeneous Biomolecules via Hierarchical Gaussian Mixtures and Part Discovery (NeurIPS 2025 · similarity 0.86)
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.
