gvnn swMATH ID: 31211 Software Authors: Ankur Handa, Michael Bloesch, Viorica Patraucean, Simon Stent, John McCormac, Andrew Davison Description: gvnn: Neural Network Library for Geometric Computer Vision. We introduce gvnn, a neural network library in Torch aimed towards bridging the gap between classic geometric computer vision and deep learning. Inspired by the recent success of Spatial Transformer Networks, we propose several new layers which are often used as parametric transformations on the data in geometric computer vision. These layers can be inserted within a neural network much in the spirit of the original spatial transformers and allow backpropagation to enable end-to-end learning of a network involving any domain knowledge in geometric computer vision. This opens up applications in learning invariance to 3D geometric transformation for place recognition, end-to-end visual odometry, depth estimation and unsupervised learning through warping with a parametric transformation for image reconstruction error. Homepage: https://arxiv.org/abs/1607.07405 Source Code: https://github.com/ankurhanda/gvnn Related Software: TensorFlow; PyTorch; Kaolin; PartNet; PointNet; GEOMetrics; MeshCNN; DeepSDF; Pixel2Mesh; Kornia; MNIST; DGM; Adam; CutFEM Cited in: 1 Publication Cited by 3 Authors 1 He, Cuiyu 1 Hu, Xiaozhe 1 Mu, Lin Cited in 1 Serial 1 Journal of Computational and Applied Mathematics Cited in 4 Fields 1 Partial differential equations (35-XX) 1 Numerical analysis (65-XX) 1 Computer science (68-XX) 1 Biology and other natural sciences (92-XX) Citations by Year