GD-MAE: Generative Decoder for MAE Pre-training on LiDAR Point Clouds.
Honghui YangTong HeJiaheng LiuHua ChenBoxi WuBinbin LinXiaofei HeWanli OuyangPublished in: CoRR (2022)
Keyphrases
- point cloud
- surface reconstruction
- structure from motion
- point sets
- point cloud data
- lidar data
- stereo camera
- laser scanner
- supervised learning
- triangular mesh
- icp algorithm
- three dimensional
- discriminative training
- multi view reconstruction
- training samples
- high resolution
- training set
- high quality
- normal vectors
- image processing