Fast-MVSNet: Sparse-to-Dense Multi-View Stereo With Learned Propagation and Gauss-Newton Refinement.
Zehao YuShenghua GaoPublished in: CVPR (2020)
Keyphrases
- multi view stereo
- gauss newton
- scene flow
- multi view
- urban environments
- depth map
- structure from motion
- point cloud
- active appearance models
- high fidelity
- bundle adjustment
- depth estimation
- optical flow
- camera parameters
- gaussian process
- d scene
- motion field
- sparse representation
- visual hull
- stereo matching
- camera calibration
- object detection
- input image