Hur, Junhwa Lim, Hwasup Park, Changsoo Ahn, Sang Chul 2024-01-19T11:40:09Z 2024-01-19T11:40:09Z 2022-03-07 2015-06-08 1063-6919 https://pubs.kist.re.kr/handle/201004/115061 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) [10] 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 high dimensional 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 state-of-the-art methods both qualitatively and quantitatively. English IEEE Generalized Deformable Spatial Pyramid: Geometry-Preserving Dense Correspondence Estimation Conference 1 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.1392 - 1400 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 1392 1400 US Boston, MA 2015-06-07 2015 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) 000387959201045 2-s2.0-84946787678