TY - GEN
T1 - Randomized texture flow estimation using visual similarity
AU - Choi, Sunghwan
AU - Min, Dongbo
AU - Sohn, Kwanghoon
N1 - Publisher Copyright:
© 2014 IEEE.
PY - 2014/1/28
Y1 - 2014/1/28
N2 - Exploring underlying texture flows defined with orientation and scale is of a great interest on a variety of vision-related tasks. However, existing methods often fail to capture accurate flows due to over-parameterization of texture deformation or employ a costly global optimization which makes the algorithm computationally demanding. In this paper, we address this inverse problem by casting it as a randomized correspondence search along with a locally-adaptive vector field smoothing. When a small example patch is given as a reference, a randomized deformable matching is performed on the very densely quantized label space, enabling an efficient estimation of texture deformation without quality degeneration, e.g., due to quantization artifacts which often appear in the optimization-driven discrete approaches. The visual similarity with respect to the deformation parameters is directly measured with an input texture image on an appearance space. The locally-adaptive smoothing is then applied to the intermediate flow field, resulting in a good continuation of the resultant texture flow. Experimental results on both synthetic and natural images show that the proposed method improves the performance in terms of both runtime efficiency and/or visual quality, compared to the existing methods.
AB - Exploring underlying texture flows defined with orientation and scale is of a great interest on a variety of vision-related tasks. However, existing methods often fail to capture accurate flows due to over-parameterization of texture deformation or employ a costly global optimization which makes the algorithm computationally demanding. In this paper, we address this inverse problem by casting it as a randomized correspondence search along with a locally-adaptive vector field smoothing. When a small example patch is given as a reference, a randomized deformable matching is performed on the very densely quantized label space, enabling an efficient estimation of texture deformation without quality degeneration, e.g., due to quantization artifacts which often appear in the optimization-driven discrete approaches. The visual similarity with respect to the deformation parameters is directly measured with an input texture image on an appearance space. The locally-adaptive smoothing is then applied to the intermediate flow field, resulting in a good continuation of the resultant texture flow. Experimental results on both synthetic and natural images show that the proposed method improves the performance in terms of both runtime efficiency and/or visual quality, compared to the existing methods.
KW - Texture analysis
KW - correspondence search
KW - flow estimation
KW - joint filtering
UR - http://www.scopus.com/inward/record.url?scp=84983122740&partnerID=8YFLogxK
U2 - 10.1109/ICIP.2014.7025945
DO - 10.1109/ICIP.2014.7025945
M3 - Conference contribution
AN - SCOPUS:84983122740
T3 - 2014 IEEE International Conference on Image Processing, ICIP 2014
SP - 4662
EP - 4666
BT - 2014 IEEE International Conference on Image Processing, ICIP 2014
PB - Institute of Electrical and Electronics Engineers Inc.
ER -