CVPR 2018 accepted papers on Point clouds
35 of the 979 papers accepted at CVPR 2018 (3.6%) are on Point clouds, compared with 1.4% at CVPR 2017. They fall into 4 topics.
See CVPR 2018 in the interactive map
Submitting to CVPR? Checklist →
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 · 16 papers
- FoldingNet: Point Cloud Auto-Encoder via Deep Grid Deformation (1,382 citations)
- SO-Net: Self-Organizing Network for Point Cloud Analysis (986 citations)
- SPLATNet: Sparse Lattice Networks for Point Cloud Processing (831 citations)
- PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition (689 citations)
- PPFNet: Global Context Aware Local Features for Robust 3D Point Matching (641 citations)
- Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling (578 citations)
- Recurrent Slice Networks for 3D Segmentation of Point Clouds (532 citations)
- PointGrid: A Deep Network for 3D Shape Understanding (462 citations)
- Attentional ShapeContextNet for Point Cloud Recognition (376 citations)
- Deep Parametric Continuous Convolutional Neural Networks (358 citations)
- Hierarchical Recurrent Attention Networks for Structured Online Maps (78 citations)
- A Network Architecture for Point Cloud Classification via Automatic Depth Images Generation (67 citations)
and 4 more in the interactive map.
Segmentation and detection · 10 papers
- VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection (4,733 citations)
- Frustum PointNets for 3D Object Detection From RGB-D Data (2,820 citations)
- 3D Semantic Segmentation With Submanifold Sparse Convolutional Networks (1,861 citations)
- Large-Scale Point Cloud Semantic Segmentation With Superpoint Graphs (1,546 citations)
- PIXOR: Real-Time 3D Object Detection From Point Clouds (1,341 citations)
- PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation (867 citations)
- Pointwise Convolutional Neural Networks (652 citations)
- Tangent Convolutions for Dense Prediction in 3D (618 citations)
- SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation (598 citations)
- A Minimalist Approach to Type-Agnostic Detection of Quadrics in Point Clouds (12 citations)
Shape and surface completion · 6 papers
- PU-Net: Point Cloud Upsampling Network (689 citations)
- Deep Marching Cubes: Learning Explicit Surface Representations (274 citations)
- Learning 3D Shape Completion From Laser Scan Data With Weak Supervision (250 citations)
- Planar Shape Detection at Structural Scales (38 citations)
- Reconstructing Thin Structures of Manifold Surfaces by Integrating Spatial Curves (32 citations)
- Reflection Removal for Large-Scale 3D Point Clouds (24 citations)
