Template Matching with

Deformable Diversity Similarity

Itamar Talmi*, Roey Mechrez* and Lihi Zelnik-Manor

* equal contribution


[Paper] [GitHub]


Template Matching results of the proposed Deformable Diversity Similarity (DDIS).
Two children faces are given as templates (middle).
Best matches found by DDIS are marked by corresponding colors on the target image (top).
The likelihood maps for each template are at the bottom (blue = low, red = high).



We propose a novel measure for template matching named Deformable Diversity Similarity -- based on the diversity of feature matches between a target image window and the template. We rely on both local appearance and geometric information that jointly lead to a powerful approach for matching. Our key contribution is a similarity measure, that is robust to complex deformations, significant background clutter, and occlusions. Empirical evaluation on the most up-to-date benchmark shows that our method outperforms the current state-of-the-art in its detection accuracy while improving computational complexity.



“Template Matching with Deformable Diversity Similarity”, to appear in CVPR 2017 [pdf] [BibTex] [Supplementary]


Try our code

Code to reporduce the experiments described in our paper is available in [GitHub]


Recent Related Work

Best-Buddies Similarity for Robust Template Matching
Tali Dekel, Shaul Oron, Michael Rubinstein, Shai Avidan, William T. Freeman [ProjectPage]