Coarse-to-Fine Multi-Scene Pose Regression with Transformers.
Yoli ShavitRon FerensYosi KellerPublished in: CoRR (2023)
Keyphrases
- coarse to fine
- multiscale
- feature correspondences
- multiresolution
- convolutional network
- object detection
- image registration
- hierarchical segmentation
- d scene
- video sequences
- facial landmarks
- active shape model
- d objects
- model selection
- hierarchical representation
- multiple images
- dynamic programming
- pose estimation
- support vector
- optical flow estimation
- three dimensional
- image sequences
- single image
- matching scheme
- camera pose
- camera calibration
- computer vision
- object recognition
- image segmentation