2020Zeng GumNet
Citation
X. Zeng and M. Xu, “Gum-net: Unsupervised geometric matching for fast and accurate 3d subtomogram image alignment and averaging,” in Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 4073–4084.
Abstract
We propose a Geometric unsupervised matching Net- work (Gum-Net) for finding the geometric correspondence between two images with application to 3D subtomogram alignment and averaging. Subtomogram alignment is the most important task in cryo-electron tomography (cryo-ET), a revolutionary 3D imaging technique for visualizing the molecular organization of unperturbed cellular landscapes in single cells. However, subtomogram alignment and av- eraging are very challenging due to severe imaging limits such as noise and missing wedge effects. We introduce an end-to-end trainable architecture with three novel modules specifically designed for preserving feature spatial informa- tion and propagating feature matching information. The training is performed in a fully unsupervised fashion to op- timize a matching metric. No ground truth transformation information nor category-level or instance-level matching supervision information is needed. After systematic assess- ments on six real and nine simulated datasets, we demon- strate that Gum-Net reduced the alignment error by 40 to 50% and improved the averaging resolution by 10%. Gum- Net also achieved 70 to 110 times speedup in practice with GPU acceleration compared to state-of-the-art subtomo- gram alignment methods. Our work is the first 3D unsu- pervised geometric matching method for images of strong transformation variation and high noise level. The train- ing code, trained model, and datasets are available in our open-source software AITom.