Template Matching with Deformable Diversity Similarity
By Itamar Talmi, Roey Mechrez, Lihi Zelnik-Manor. 2016
105 citations recorded by the source corpus.
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.
Subfields: Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Ming-Hsuan Yang
- Dacheng Tao
- Andrea Vedaldi
- Xiaogang Wang
- Andrew Zisserman
- Jitendra Malik
- Trevor Darrell
Citations in the corpus
- A critical analysis of self-supervision, or what we can learn from a single image (2019, background): “Example applications that only rely on low-level feature extractors include template matching (Kat et al., 2018; Talmi et al., 2017) and style transfer (Gatys et al.”
- Matching Pixels Using Co-occurrence Statistics (2018, methodology): “We compare CoTM, on both color and deep feature images, to two state-of-the-art measures for template matching: Deformable Diversity Similarity [27] (DDIS) and BestBuddies Similarity [5] (BBS).”
- The Contextual Loss for Image Transformation with Non-Aligned Data (2018, methodology): “Finally, similar to [31,33], one can show that this holds also for the multi-dimensional case.”
- Neural best-buddies (2018, methodology): “This method was previously leveraged for tasks such as image matching [Li et al. 2015], classification of images, etc., and extended to the Best-Buddies similarity concept, which measures similarity between patches [Dekel et al. 2015; Talmi et al. 2017] for the purpose of template matching.”