Physics-inspired structural representations for molecules and materials
The first step in the construction of a regression model or a data-driven analysis, aiming to
predict or elucidate the relationship between the atomic-scale structure of matter and its …
predict or elucidate the relationship between the atomic-scale structure of matter and its …
Review of multi-view 3D object recognition methods based on deep learning
Abstract Three-dimensional (3D) object recognition is widely used in automated driving,
medical image analysis, virtual/augmented reality, artificial intelligence robots, and other …
medical image analysis, virtual/augmented reality, artificial intelligence robots, and other …
Pointflow: 3d point cloud generation with continuous normalizing flows
As 3D point clouds become the representation of choice for multiple vision and graphics
applications, the ability to synthesize or reconstruct high-resolution, high-fidelity point clouds …
applications, the ability to synthesize or reconstruct high-resolution, high-fidelity point clouds …
Mvtn: Multi-view transformation network for 3d shape recognition
Multi-view projection methods have demonstrated their ability to reach state-of-the-art
performance on 3D shape recognition. Those methods learn different ways to aggregate …
performance on 3D shape recognition. Those methods learn different ways to aggregate …
Foldingnet: Point cloud auto-encoder via deep grid deformation
Recent deep networks that directly handle points in a point set, eg, PointNet, have been
state-of-the-art for supervised learning tasks on point clouds such as classification and …
state-of-the-art for supervised learning tasks on point clouds such as classification and …
PointNet: Deep learning on point sets for 3D classification and segmentation
RQ Charles, H Su, M Kaichun… - 2017 IEEE conference …, 2017 - ieeexplore.ieee.org
Point cloud is an important type of geometric data structure. Due to its irregular format, most
researchers transform such data to regular 3D voxel grids or collections of images. This …
researchers transform such data to regular 3D voxel grids or collections of images. This …
Learning representations and generative models for 3d point clouds
P Achlioptas, O Diamanti… - … on machine learning, 2018 - proceedings.mlr.press
Three-dimensional geometric data offer an excellent domain for studying representation
learning and generative modeling. In this paper, we look at geometric data represented as …
learning and generative modeling. In this paper, we look at geometric data represented as …
Gvcnn: Group-view convolutional neural networks for 3d shape recognition
Abstract 3D shape recognition has attracted much attention recently. Its recent advances
advocate the usage of deep features and achieve the state-of-the-art performance. However …
advocate the usage of deep features and achieve the state-of-the-art performance. However …
Pointnet: Deep learning on point sets for 3d classification and segmentation
Point cloud is an important type of geometric data structure. Due to its irregular format, most
researchers transform such data to regular 3D voxel grids or collections of images. This …
researchers transform such data to regular 3D voxel grids or collections of images. This …
Opening the black box of deep neural networks via information
R Shwartz-Ziv, N Tishby - arxiv preprint arxiv:1703.00810, 2017 - arxiv.org
Despite their great success, there is still no comprehensive theoretical understanding of
learning with Deep Neural Networks (DNNs) or their inner organization. Previous work …
learning with Deep Neural Networks (DNNs) or their inner organization. Previous work …