LIP-Loc: LiDAR Image Pretraining for Cross-Modal Localization.
Sai Shubodh PuligillaMohammad OmamaHusain ZaidiUdit Singh PariharK. Madhava KrishnaPublished in: CoRR (2023)
Keyphrases
- cross modal
- input image
- image retrieval
- image content
- multiscale
- image features
- image data
- image classification
- high resolution
- visual data
- image representation
- object localization
- image segmentation
- multi modal
- image collections
- low level
- scene classification
- multimedia retrieval
- visual similarity
- similarity measure
- keypoints
- image regions
- visual recognition
- feature vectors