MRNet: Multiple-Input Receptive Field Network for Large-Scale Point Cloud Segmentation.
Sunghwan YooYeongjeong JeongMaryam JameelaGunho SohnPublished in: CoRR (2023)
Keyphrases
- point cloud
- multiple input
- receptive fields
- biologically inspired
- structure from motion
- natural images
- multiscale
- point sets
- image representation
- primary visual cortex
- image data
- image segmentation
- visual cortex
- principal component analysis
- image features
- neural network
- camera motion
- object recognition
- video sequences
- input space
- image processing
- laser scanner
- machine learning