We present recurrent transformer networks (RTNs) for obtaining dense correspondences
between semantically similar images. Our networks accomplish this through an iterative …

We address estimating dense correspondences between two images depicting different but
semantically related scenes. End-to-end trainable deep neural networks incorporating …

This paper presents a deep architecture for dense semantic correspondence, called
pyramidal affine regression networks (PARN), that estimates locally-varying affine …

Dense correspondence across semantically related images has been extensively studied,
but still faces two challenges: 1) large variations in appearance, scale and pose exist even …

This paper addresses the problem of establishing semantic correspondences between
images depicting different instances of the same object or scene category. Previous …

We study the problem of learning semantic image correspondences without manual
supervision. Previous works that tackled this problem rely on manually curated image pairs …

Despite significant progress of deep learning in recent years, state-of-the-art semantic
matching methods still rely on legacy features such as SIFT or HoG. We argue that the …

Establishing dense correspondences across semantically similar images remains a
challenging task due to the significant intra-class variations and background clutters …

Establishing correspondences between images remains a challenging task, especially
under large appearance changes due to different viewpoints or intra-class variations. In this …

Establishing visual correspondences under large intra-class variations, which is often
referred to as semantic correspondence or semantic matching, remains a challenging …