Hybridnet for Depth Estimation and Semantic Segmentation.
Dalila Sánchez-EscobedoXiao LinJosep R. CasasMontse PardàsPublished in: ICASSP (2018)
Keyphrases
- depth estimation
- street scenes
- semantic segmentation
- stereo vision
- depth map
- stereo matching
- dynamic scenes
- depth information
- stereo pair
- super resolution
- scene understanding
- conditional random fields
- feature matching
- real scenes
- scene classification
- weakly supervised
- superpixels
- object categories
- high quality
- d scene
- stereo images
- single image
- high resolution