NeuroMorph: Unsupervised Shape Interpolation and Correspondence in One Go

Marvin Eisenberger, David Novotny, Gael Kerchenbaum, Patrick Labatut, Natalia Neverova, Daniel Cremers, Andrea Vedaldi; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 7473-7483

Abstract


We present NeuroMorph, a new neural network architecture that takes as input two 3D shapes and produces in one go, i.e. in a single feed forward pass, a smooth interpolation and point-to-point correspondences between them. The interpolation, expressed as a deformation field, changes the pose of the source shape to resemble the target, but leaves the object identity unchanged. NeuroMorph uses an elegant architecture combining graph convolutions with global feature pooling to extract local features. During training, the model is incentivized to create realistic deformations by approximating geodesics on the underlying shape space manifold. This strong geometric prior allows to train our model end-to-end and in a fully unsupervised manner without requiring any manual correspondence annotations. NeuroMorph works well for a large variety of input shapes, including non-isometric pairs from different object categories. It obtains state-of-the-art results for both shape correspondence and interpolation tasks, matching or surpassing the performance of recent unsupervised and supervised methods on multiple benchmarks.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Eisenberger_2021_CVPR, author = {Eisenberger, Marvin and Novotny, David and Kerchenbaum, Gael and Labatut, Patrick and Neverova, Natalia and Cremers, Daniel and Vedaldi, Andrea}, title = {NeuroMorph: Unsupervised Shape Interpolation and Correspondence in One Go}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2021}, pages = {7473-7483} }