ICCV 2019 accepted papers on Point clouds
43 of the 1,075 papers accepted at ICCV 2019 (4.0%) are on Point clouds, compared with 1.9% at ICCV 2017. They fall into 4 topics.
See ICCV 2019 in the interactive map
Submitting to ICCV? 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
Shape and surface completion · 16 papers
- PointFlow: 3D Point Cloud Generation With Continuous Normalizing Flows (714 citations)
- PU-GAN: A Point Cloud Upsampling Adversarial Network (546 citations)
- Point-Based Multi-View Stereo Network (417 citations)
- Implicit Surface Representations As Layers in Neural Networks (252 citations)
- Occupancy Flow: 4D Reconstruction by Learning Particle Dynamics (249 citations)
- USIP: Unsupervised Stable Interest Point Detection From 3D Point Clouds (215 citations)
- GarNet: A Two-Stream Network for Fast and Accurate 3D Cloth Draping (159 citations)
- Total Denoising: Unsupervised Learning of 3D Point Cloud Cleaning (143 citations)
- Multi-Angle Point Cloud-VAE: Unsupervised Feature Learning for 3D Point Clouds From Multiple Angles by Joint Self-Reconstruction and Half-to-Half Prediction (129 citations)
- BAE-NET: Branched Autoencoder for Shape Co-Segmentation (122 citations)
- GLAMpoints: Greedily Learned Accurate Match Points (84 citations)
- Asynchronous Single-Photon 3D Imaging (82 citations)
and 4 more in the interactive map.
Point cloud classification · 16 papers
- KPConv: Flexible and Deformable Convolution for Point Clouds (3,574 citations)
- Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data (948 citations)
- Fully Convolutional Geometric Features (852 citations)
- ShellNet: Efficient Point Cloud Convolutional Neural Networks Using Concentric Shells Statistics (437 citations)
- LPD-Net: 3D Point Cloud Learning for Large-Scale Place Recognition and Environment Analysis (345 citations)
- VV-Net: Voxel VAE Net With Group Convolutions for Point Cloud Segmentation (331 citations)
- DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processing (311 citations)
- 3D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutions (282 citations)
- PointCloud Saliency Maps (269 citations)
- Interpolated Convolutional Networks for 3D Point Cloud Understanding (251 citations)
- MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequences (236 citations)
- Unsupervised Multi-Task Feature Learning on Point Clouds (200 citations)
and 4 more in the interactive map.
Segmentation and detection · 8 papers
- SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences (2,416 citations)
- Deep Hough Voting for 3D Object Detection in Point Clouds (1,291 citations)
- STD: Sparse-to-Dense 3D Object Detector for Point Cloud (894 citations)
- Fast Point R-CNN (412 citations)
- Accurate Monocular 3D Object Detection via Color-Embedded 3D Reconstruction for Autonomous Driving (340 citations)
- Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentation (223 citations)
- Generative Adversarial Training for Weakly Supervised Cloud Matting (40 citations)
- Learning Propagation for Arbitrarily-Structured Data
