Recurrent Multi-view Alignment Network for Unsupervised Surface Registration
This work provides a novel unsupervised learning approach for non-rigid surface registration, which is a critical problem for applications in computer vision and medical imaging where labeled data is scarce.
This paper addresses unsupervised non-rigid surface registration by representing transformations as a point-wise combination of rigid transformations, enabling an iterative recurrent solution. It introduces a differentiable multi-view 2D depth image similarity loss, achieving state-of-the-art performance on multiple datasets.
Learning non-rigid registration in an end-to-end manner is challenging due to the inherent high degrees of freedom and the lack of labeled training data. In this paper, we resolve these two challenges simultaneously. First, we propose to represent the non-rigid transformation with a point-wise combination of several rigid transformations. This representation not only makes the solution space well-constrained but also enables our method to be solved iteratively with a recurrent framework, which greatly reduces the difficulty of learning. Second, we introduce a differentiable loss function that measures the 3D shape similarity on the projected multi-view 2D depth images so that our full framework can be trained end-to-end without ground truth supervision. Extensive experiments on several different datasets demonstrate that our proposed method outperforms the previous state-of-the-art by a large margin. The source codes are available at https://github.com/WanquanF/RMA-Net.