WikiSysop: Created page with "== Citation == Zhang, J., Zhou, S., Dai, H., Liu, X., Wang, P., Fan, Z., Pei, Y. and Yu, J. 2025. CryoFastAR: Fast Cryo-EM Ab Initio Reconstruction Made Easy. 2025 IEEE/CVF International Conference on Computer Vision (ICCV) (2025), 8462–8471. == Abstract == Pose estimation from unordered images is fundamental for 3D reconstruction, robotics, and scientific imaging. Recent geometric foundation models, such as DUSt3R, enable end-to-end dense 3D reconstruction but rema..."

2026-08-12T04:36:27Z

Created page with "== Citation == Zhang, J., Zhou, S., Dai, H., Liu, X., Wang, P., Fan, Z., Pei, Y. and Yu, J. 2025. CryoFastAR: Fast Cryo-EM Ab Initio Reconstruction Made Easy. 2025 IEEE/CVF International Conference on Computer Vision (ICCV) (2025), 8462–8471. == Abstract == Pose estimation from unordered images is fundamental for 3D reconstruction, robotics, and scientific imaging. Recent geometric foundation models, such as DUSt3R, enable end-to-end dense 3D reconstruction but rema..."

New page

== Citation ==

Zhang, J., Zhou, S., Dai, H., Liu, X., Wang, P., Fan, Z., Pei, Y. and Yu, J. 2025. CryoFastAR: Fast Cryo-EM Ab Initio Reconstruction Made Easy. 2025 IEEE/CVF International Conference on Computer Vision (ICCV) (2025), 8462–8471.

== Abstract ==

Pose estimation from unordered images is fundamental for
3D reconstruction, robotics, and scientific imaging. Recent
geometric foundation models, such as DUSt3R, enable
end-to-end dense 3D reconstruction but remain underexplored
in scientific imaging fields like cryo-electron microscopy
(cryo-EM) for near-atomic protein reconstruction.
In cryo-EM, pose estimation and 3D reconstruction from
unordered particle images still depend on time-consuming
iterative optimization, primarily due to challenges such as
low signal-to-noise ratios (SNR) and distortions from the
contrast transfer function (CTF). We introduce CryoFastAR,
the first geometric foundation model that can directly
predict poses from Cryo-EM noisy images for Fast ab initio
Reconstruction. By integrating multi-view features and
training on large-scale simulated cryo-EM data with realistic
noise and CTF modulations, CryoFastAR enhances
pose estimation accuracy and generalization. To enhance
training stability, we propose a progressive training strategy
that first allows the model to extract essential features under
simpler conditions before gradually increasing difficulty
to improve robustness. Experiments show that CryoFastAR
achieves comparable quality while significantly accelerating
inference over traditional iterative approaches on both
synthetic and real datasets. We will release our code, models,
and datasets to stimulate further research.

== Keywords ==

== Links ==

https://ieeexplore.ieee.org/abstract/document/11445565

== Related software ==

== Related methods ==

== Comments ==

2025Zhang CryoFastAR - Revision history