Deep Reinforcement Learning of Volume-guided Progressive View Inpainting for 3D Point Scene Completion from a Single Depth Image.
Xiaoguang HanZhaoxuan ZhangDong DuMingdai YangJingming YuPan PanXin YangLigang LiuZixiang XiongShuguang CuiPublished in: CoRR (2019)
Keyphrases
- depth images
- reinforcement learning
- virtual view
- depth information
- three dimensional
- pose estimation
- planar surfaces
- d scene
- depth cameras
- view dependent
- depth data
- depth map
- time of flight
- machine learning
- single image
- low resolution
- denoising
- video sequences
- image processing
- stereo vision
- input data
- color information
- multiple objects
- outdoor scenes
- high resolution
- face recognition
- computer vision
- learning algorithm