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