GeoMIM: Towards Better 3D Knowledge Transfer via Masked Image Modeling for Multi-view 3D Understanding.
Jihao LiuTai WangBoxiao LiuQihang ZhangYu LiuHongsheng LiPublished in: ICCV (2023)
Keyphrases
- multi view
- knowledge transfer
- single view
- input image
- multiple views
- multi view images
- multi views
- depth map
- camera calibration
- d objects
- semi supervised
- three dimensional
- image classification
- single image
- image features
- knowledge sharing
- test images
- image segmentation
- feature points
- transfer learning
- view synthesis
- visual hull
- machine learning
- multi view learning
- co training
- high resolution
- viewpoint
- information extraction
- range images
- text categorization
- computer vision