Marie-Julie Rakotosaona

TL;DR: Poulenard et al. as mentioned in this paper proposed a rotation invariant point-cloud point-based convolutional neural network (SPHnet), which is guaranteed to be invariant to rigid motions.

TL;DR: SPARF as discussed by the authors exploits multi-view geometry constraints in order to jointly learn the NeRF and refine the camera poses, by relying on pixel matches extracted between the input views, which enforces the optimized scene and camera poses to converge to a global and geometrically accurate solution.

TL;DR: This work demonstrates how rotation invariance can be injected into a recently proposed point-based PCNN architecture, on all layers of the network, and achieves accurate results on challenging shape analysis tasks, without requiring data-augmentation typically employed by non-invariant approaches.

TL;DR: In this paper, a simple data-driven method for removing outliers and reducing noise in unordered point clouds is proposed, based on a deep learning architecture adapted from PCPNet, which was recently proposed for estimating local 3D shape properties.