Accurate Ground-Truth Depth Image Generation via Overfit Training of Point Cloud Registration using Local Frame Sets.
Jiwan KimMinchang KimYeong-Gil ShinMinyoung ChungPublished in: CoRR (2022)
Keyphrases
- point cloud
- image generation
- ground truth
- lidar data
- surface reconstruction
- high quality
- high resolution
- structure from motion
- laser scanner
- point sets
- virtual view
- depth map
- training set
- stereo camera
- digital imaging
- image processing
- depth information
- highly accurate
- image sequences
- view synthesis
- photorealistic
- missing data