SOSD-Net: Joint Semantic Object Segmentation and Depth Estimation from Monocular images.
Lei HeJiwen LuGuanghui WangShiyu SongJie ZhouPublished in: CoRR (2021)
Keyphrases
- monocular images
- object segmentation
- depth estimation
- stereo vision
- object detection
- depth map
- scene understanding
- graph cuts
- stereo matching
- image segmentation
- depth information
- segmentation method
- foreground objects
- shape prior
- segmentation algorithm
- stereo pair
- super resolution
- dynamic scenes
- human body
- object categories
- pose estimation
- real scenes
- feature matching
- human pose
- image sequences
- optical flow
- d scene
- object recognition