ECCV 2018 accepted papers on Point clouds
17 of the 776 papers accepted at ECCV 2018 (2.2%) are on Point clouds, compared with 2.2% at ECCV 2016. They fall into 4 topics.
See ECCV 2018 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Point cloud classification · 9 papers
- SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters (887 citations)
- PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors (415 citations)
- Local Spectral Graph Convolution for Point Set Feature Learning (406 citations)
- Multiresolution Tree Networks for 3D Point Cloud Processing (247 citations)
- Fully-Convolutional Point Networks for Large-Scale Point Clouds (216 citations)
- HGMR: Hierarchical Gaussian Mixtures for Adaptive 3D Registration (127 citations)
- A-Contrario Horizon-First Vanishing Point Detection Using Second-Order Grouping Laws (31 citations)
- Perturbation Robust Representations of Topological Persistence Diagrams (20 citations)
- Proxy Clouds for Live RGB-D Stream Processing and Consolidation (3 citations)
Shape and surface completion · 4 papers
- EC-Net: an Edge-aware Point set Consolidation Network (326 citations)
- GAL: Geometric Adversarial Loss for Single-View 3D-Object Reconstruction (130 citations)
- Learning and Matching Multi-View Descriptors for Registration of Point Clouds (50 citations)
- Fast and Accurate Intrinsic Symmetry Detection (23 citations)
