Depth-Guided Sparse Structure-from-Motion for Movies and TV Shows.
Sheng LiuXiaohan NieRaffay HamidPublished in: CoRR (2022)
Keyphrases
- structure from motion
- closed captions
- tv shows
- scene depth
- bundle adjustment
- image sequences
- topic segmentation
- motion estimates
- camera parameters
- point cloud
- missing data
- depth map
- computer vision
- focal length
- human interactions
- high dimensional
- camera motion
- feature tracking
- video clips
- depth estimates
- depth information
- camera pose
- optical flow
- object recognition
- machine learning