IMENet: Joint 3D Semantic Scene Completion and 2D Semantic Segmentation through Iterative Mutual Enhancement.
Jie LiLaiyan DingRui HuangPublished in: CoRR (2021)
Keyphrases
- semantic segmentation
- scene classification
- superpixels
- object recognition
- natural scenes
- label transfer
- multiple images
- biologically inspired
- visual words
- weakly supervised
- image classification
- image set
- conditional random fields
- bag of words
- three dimensional
- semantic information
- input image
- single image
- object categories
- pascal voc
- video sequences
- image representation
- image understanding
- natural language
- semantic features
- pixel level
- viewpoint
- visual features
- object classes
- low level features
- image sequences
- image processing