Learning to Fuse Monocular and Multi-view Cues for Multi-frame Depth Estimation in Dynamic Scenes.
Rui LiDong GongWei YinHao ChenYu ZhuKaixuan WangXiaozhi ChenJinqiu SunYanning ZhangPublished in: CoRR (2023)
Keyphrases
- dynamic scenes
- multi view
- depth estimation
- depth map
- single view
- multiple views
- ego motion
- multiple cameras
- d objects
- motion segmentation
- camera calibration
- image sequences
- multi frame
- background subtraction
- three dimensional
- range images
- pose estimation
- space time
- stereo correspondence
- foreground objects
- moving camera
- surface reconstruction
- moving objects
- frame rate
- semi supervised
- video sequences
- multiscale
- machine learning
- depth information
- motion estimation
- pairwise
- point correspondences
- video frames