Research map / 3D vision / Human pose estimation
CryoFastAR: Fast Cryo-EM Ab initio Reconstruction Made Easy
Jiakai Zhang, Shouchen Zhou, Haizhao Dai, Xinhang Liu, Peihao Wang, Zhiwen Fan, Yuan Pei, Jingyi Yu
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 CryoSPARC local refinement to CryoFastAR poses | CryoFastAR · Spliceosome(Sim) simulated | rotation F-norm error: 0.0597 -> 0.0148 | Improved |
| add CryoSPARC refinement to CryoFastAR poses | CryoFastAR · Spike simulated | rotation F-norm error: 0.0416 -> 0.0151 | Improved |
| add CryoSPARC refinement to CryoFastAR poses | CryoFastAR · FA simulated | FSC resolution (A): 6.64 -> 5.33 | Improved |
| add CryoSPARC refinement to CryoFastAR poses | CryoFastAR · Spliceosome real | rotation F-norm error: 0.9564 -> 0.9734 | Hurt |
| add CryoSPARC refinement to CryoFastAR poses | CryoFastAR · 50S real | rotation F-norm error: 1.1521 -> 0.9355 | Improved |
| increase input views from 32 to 128 (ablation) | CryoFastAR · simulated, SNR 0.1 | rotation F-norm error: 12.6% | Improved |
| increase input views from 32 to 128 (ablation) | CryoFastAR · simulated, SNR 0.1 | 2D in-plane translation error: 3.94% | Improved |
| evaluate at SNR 0.05 (half of training SNR 0.1) (ablation) | CryoFastAR · simulated | pose error: 0.05 | No clear effect |
| use CryoFastAR instead of CryoSPARC for initial reconstruction | CryoFastAR · real datasets | reconstruction time: 3.33 | Improved |
| use CryoFastAR instead of CryoSPARC on 50S ribosome | CryoFastAR · 50S real | rotation F-norm error: 0.2110 -> 1.1521 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- CryoDRGN2 — CryoDRGN2: Ab Initio Neural Reconstruction of 3D Protein Structures From Real Cryo-EM Images (ICCV 2021) · better on 5 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- CryoSPIN: Improving Ab-Initio Cryo-EM Reconstruction with Semi-Amortized Pose Inference (NeurIPS 2024 · similarity 0.93)
- cryoSPHERE: Single-Particle HEterogeneous REconstruction from cryo EM (ICLR 2025 · similarity 0.91)
- CryoBench: Diverse and challenging datasets for the heterogeneity problem in cryo-EM (NeurIPS 2024 · similarity 0.89)
- CryoFM: A Flow-based Foundation Model for Cryo-EM Densities (ICLR 2025 · similarity 0.89)
- Reconstructing Heterogeneous Biomolecules via Hierarchical Gaussian Mixtures and Part Discovery (NeurIPS 2025 · similarity 0.89)
- CryoGEM: Physics-Informed Generative Cryo-Electron Microscopy (NeurIPS 2024 · similarity 0.88)
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.
