MiniNet: An extremely lightweight convolutional neural network for real-time unsupervised monocular depth estimation.
Jun LiuQing LiRui CaoWenming TangGuoping QiuPublished in: CoRR (2020)
Keyphrases
- lightweight
- depth estimation
- monocular images
- convolutional neural network
- real time
- depth map
- depth cues
- stereo vision
- stereo matching
- real scenes
- image sequences
- low cost
- super resolution
- depth estimates
- vision system
- pose estimation
- face detection
- scene understanding
- viewpoint
- pairwise
- image processing
- d scene
- belief propagation
- stereo pair
- multi view
- wireless sensor networks
- high quality