Transformers in Unsupervised Structure-from-Motion.
Hemang ChawlaArnav VarmaElahe AraniBahram ZonoozPublished in: VISIGRAPP (Revised Selected Papers) (2022)
Keyphrases
- structure from motion
- bundle adjustment
- camera parameters
- image sequences
- missing data
- computer vision
- feature tracking
- point cloud
- camera motion
- reconstruction from multiple images
- camera positions
- image based localization
- focal length
- reprojection error
- long image sequences
- relative pose
- scene depth
- semi supervised
- scene structure
- multi view
- multibody
- line correspondences
- camera pose estimation