Self-Supervised Image-to-Point Distillation via Semantically Tolerant Contrastive Loss.
Anas MahmoudJordan S. K. HuTianshu KuaiAli HarakehLiam PaullSteven L. WaslanderPublished in: CVPR (2023)
Keyphrases
- image data
- single image
- input image
- image features
- multiscale
- image analysis
- image representation
- test images
- template matching
- image content
- edge detection
- image matching
- grey level
- feature points
- image regions
- vector field
- region of interest
- image collections
- low level
- high resolution
- similarity measure
- image structure
- matching process
- computer vision
- line features
- range images
- spatial information
- energy function
- pose estimation
- gray level
- image retrieval