Joint optimisation for object class segmentation and dense stereo reconstruction
The problems of dense stereo reconstruction and object class segmentation can both be formulated as Conditional Random Field based labelling problems, in which every pixel in the image is assigned a label corresponding to either its disparity, or an object class such as road or building. While these...
Main Authors: | Ladický, L, Sturgess, P, Russell, C, Sengupta, S, Bastanlar, Y, Clocksin, W, Torr, PHS |
---|---|
Format: | Conference item |
Language: | English |
Published: |
British Machine Vision Association
2010
|
Similar Items
-
Joint optimization for object class segmentation and dense stereo reconstruction
by: Ladický, L, et al.
Published: (2011) -
Automatic dense visual semantic mapping from street-level imagery
by: Sengupta, S, et al.
Published: (2012) -
Associative hierarchical CRFs for object class image segmentation
by: Ladický, L, et al.
Published: (2009) -
Dense semantic image segmentation with objects and attributes
by: Zheng, S, et al.
Published: (2014) -
Scalable cascade inference for semantic image segmentation
by: Sturgess, P, et al.
Published: (2012)