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 …

Deep features have been proven powerful in building accurate dense semantic
correspondences in various previous works. However, the multi-scale and pyramidal …

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

Establishing dense semantic correspondences between object instances remains a
challenging problem due to background clutter, significant scale and pose differences, and …

Recent studies show that leveraging the match-wise relationships within the 4D correlation
map yields significant improvements in establishing semantic correspondences-but at the …

We address the problem of semantic correspondence, that is, establishing a dense flow field
between images depicting different instances of the same object or scene category. We …

This paper introduces a Transformer-based integrative feature and cost aggregation network
designed for dense matching tasks. In the context of dense matching, many works benefit …

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

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