Deformable Spatial Pyramid Matching for Fast Dense Correspondences
Jaechul Kim1, Ce Liu2, Fei Sha3, Kristen Grauman1
University of Texas at Austin1, Microsoft Research New England2, University of Southern Califonia3
[pdf] [code]
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 LabelMe and Caltech show our approach outperforms state-of-the-art methods (SIFT Flow and Patch-Match), both in terms of accuracy and run time.
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 LabelMe and Caltech show our approach outperforms state-of-the-art methods (SIFT Flow and Patch-Match), both in terms of accuracy and run time.
Papers
[1] Deformable Spatial Pyramid Matching for Fast Dense Correspondences, J. Kim, C. Liu, F. Sha, K. Grauman, CVPR 2013 [pdf] [code]
Last modified 9-23-2013