Title :
Deformable Spatial Pyramid Matching for Fast Dense Correspondences
Author :
Jaechul Kim ; Ce Liu ; Fei Sha ; Grauman, Kristen
Author_Institution :
Univ. of Texas at Austin, Austin, TX, USA
Abstract :
We introduce a fast deformable spatial pyramid (DSP) matching algorithm for computing dense pixel correspondences. Dense matching methods typically enforce both appearance agreement between matched pixels as well as geometric smoothness between neighboring pixels. Whereas the prevailing approaches operate at the pixel level, we propose a pyramid graph model that simultaneously regularizes match consistency at multiple spatial extents-ranging from an entire image, to coarse grid cells, to every single pixel. This novel regularization substantially improves pixel-level matching in the face of challenging image variations, while the "deformable" aspect of our model overcomes the strict rigidity of traditional spatial pyramids. Results on Label Me and Caltech show our approach outperforms state-of-the-art methods (SIFT Flow [15] and Patch-Match [2]), both in terms of accuracy and run time.
Keywords :
graph theory; image matching; image segmentation; Caltech; DSP matching algorithm; Label Me; appearance agreement; dense matching methods; dense pixel correspondences; fast deformable spatial pyramid matching algorithm; fast dense correspondences; geometric smoothness; image variations; match consistency regularization; matched pixels; neighboring pixels; pixel-level matching; pyramid graph model; Accuracy; Digital signal processing; Image edge detection; Image matching; Optimization; Spatial resolution;
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on
Conference_Location :
Portland, OR
DOI :
10.1109/CVPR.2013.299