Multi-Frame Self-Supervised Depth Estimation with Multi-Scale Feature Fusion in Dynamic Scenes.
Jiquan ZhongXiaolin HuangXiao YuPublished in: ACM Multimedia (2023)
Keyphrases
- dynamic scenes
- depth estimation
- multi frame
- multiscale
- optic flow
- motion estimation
- video sequences
- motion segmentation
- image sequences
- point correspondences
- multi view
- space time
- super resolution
- multiple views
- moving objects
- optical flow
- motion analysis
- background subtraction
- scale space
- frame rate
- flow field
- image segmentation
- video frames
- motion field
- foreground objects
- spatio temporal
- image processing
- keypoints
- depth map
- stereo vision
- object tracking