SPU-Net: Self-Supervised Point Cloud Upsampling by Coarse-to-Fine Reconstruction with Self-Projection Optimization.
Xinhai LiuXinchen LiuZhizhong HanYu-Shen LiuPublished in: CoRR (2020)
Keyphrases
- coarse to fine
- point cloud
- multiresolution
- multiscale
- hierarchical segmentation
- object detection
- point sets
- structure from motion
- surface reconstruction
- visual hull
- image registration
- laser scanner
- implicit surfaces
- optical flow estimation
- stereo camera
- matching scheme
- point cloud data
- dynamic programming
- high resolution
- real world objects
- active shape model
- range images
- low resolution
- training data
- three dimensional
- knn
- reinforcement learning