-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chen_2022_CVPR, author = {Chen, Jiayi and Yin, Yingda and Birdal, Tolga and Chen, Baoquan and Guibas, Leonidas J. and Wang, He}, title = {Projective Manifold Gradient Layer for Deep Rotation Regression}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {6646-6655} }
Projective Manifold Gradient Layer for Deep Rotation Regression
Abstract
Regressing rotations on SO(3) manifold using deep neural networks is an important yet unsolved problem. The gap between the Euclidean network output space and the non-Euclidean SO(3) manifold imposes a severe challenge for neural network learning in both forward and backward passes. While several works have proposed different regression-friendly rotation representations, very few works have been devoted to improving the gradient backpropagating in the backward pass. In this paper, we propose a manifold-aware gradient that directly backpropagates into deep network weights. Leveraging Riemannian optimization to construct a novel projective gradient, our proposed regularized projective manifold gradient (RPMG) method helps networks achieve new state-of-the-art performance in a variety of rotation estimation tasks. Our proposed gradient layer can also be applied to other smooth manifolds such as the unit sphere. Our project page is at https://jychen18.github.io/RPMG.
Related Material