L2G Auto-encoder: Understanding Point Clouds by Local-to-Global Reconstruction with Hierarchical Self-Attention.
Xinhai LiuZhizhong HanXin WenYu-Shen LiuMatthias ZwickerPublished in: ACM Multimedia (2019)
Keyphrases
- point cloud
- architectural scenes
- urban scenes
- surface reconstruction
- structure from motion
- multi view stereo
- visual hull
- point sets
- implicit surfaces
- image reconstruction
- triangular mesh
- three dimensional
- multi view reconstruction
- reconstructed surface
- reconstruction method
- laser scanner
- stereo camera
- point cloud data
- cad model
- motion estimation
- computer vision
- optical flow
- normal vectors
- lidar data
- rigid registration
- feature vectors
- high resolution