Generalized Deformable Spatial Pyramid: Geometry-Preserving Dense Correspondence Estimation
- Generalized Deformable Spatial Pyramid: Geometry-Preserving Dense Correspondence Estimation
- 허준화; 임화섭; 박창수; 안상철
- Issue Date
- CVPR, IEEE conf. on Computer Vision and Pattern Recognition
- VOL 1, NO 1, 1392-1400
- We present a Generalized Deformable Spatial Pyramid (GDSP) matching algorithm for calculating the dense correspondence between a pair of images with large appearance variations. The main challenges of the problem generally originate in appearance dissimilarities and geometric variations between images. To address these challenges, we improve the existing Deformable Spatial Pyramid (DSP)  model by generalizing the search space and devising the spatial smoothness. The former is leveraged by rotations and scales, and the latter simultaneously considers
dependencies between high-dimensional labels through the pyramid structure. Our spatial regularization in the highdimensional space enables our model to effectively preserve the meaningful geometry of objects in the input images while allowing for a wide range of geometry variations
such as perspective transform and non-rigid deformation. The experimental results on public datasets and challenging scenarios show that our method outperforms the stateof- the-art methods both qualitatively and quantitatively.
- Appears in Collections:
- KIST Publication > Conference Paper
- Files in This Item:
There are no files associated with this item.
- RIS (EndNote)
- XLS (Excel)
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.