Pop-Net: Encoder-Dual Decoder for Semantic Segmentation and Single-View Height Estimation.
Zhuo ZhengYanfei ZhongJunjue WangPublished in: IGARSS (2019)
Keyphrases
- single view
- semantic segmentation
- multi view
- multiple views
- scene classification
- conditional random fields
- superpixels
- object categories
- motion estimation
- weakly supervised
- surface reconstruction
- object classes
- pascal voc
- viewpoint
- video sequences
- object class
- object recognition
- learning algorithm
- bit rate
- natural images
- three dimensional