Correspondence Networks with Adaptive Neighbourhood Consensus

Li, Shuda; Han, Kai; Costain, Theo W.; Howard-Jenkins, Henry; Prisacariu, Victor Adrian

doi:10.48550/arxiv.2003.12059

Cited by 1 publication

(1 citation statement)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…NCNet [21] proposes to directly learn correspondences in an end-to-end manner, which uses all points in the feature map to compute 4D tensors to construct all possible matches and uses 4D convolutions to normalize the 4D tensors. Inspired by NCNet, several methods have been proposed to improve this framework, [45], [46] by using self-similarity to capture complex local patterns for matching. Sparse-NCNet [22] notices problems of NCNet in memory and computation and solves this problem by introducing sparse convolution, which makes computation more efficient.…”

Section: B End-to-end Based Matchingmentioning

confidence: 99%

Multi-Scale Attention and Structural Relation Graph for Local Feature Matching

Nan

Ding

2022

IEEE Access

View full text Add to dashboard Cite

Building a dense correspondence between two images is a fundamental vision problem. Most existing methods use local features, but global features cannot be ignored. Local features are often not enough to disambiguate similar regions without global features. Computing relevant features between images requires structural relationship and the importance of local features. For that, We propose novel multi-scale attention and structural relation graph (MASRG) for local feature matching. The MASRG adopts an overall architecture that first builds coarse-level matches on a coarse feature map and then refines fine matches on a fine-level feature map. We propose a structural relation graph module and a multi-scale attention module. We introduce global context information into the overall architecture. Using global information to separately assist in learning the structural information between local descriptors, the features of different receptive fields, and the importance of modeling single local information, a limited number of possible matches can be obtained with high confidence. Finally, the matching relationship is predicted. In this way, the network significantly improves the matching reliability and localization accuracy. Our proposed method has 5.6%, 6.7%, and 6.3% performance increases over the baseline method(See I) under different conditions in the HPatches. Extensive experiments on three large-scale datasets (i.e., HPatches, InLoc, and Aachen Day-Night v1.1) demonstrate that our proposed MASRG method is superior to state-of-the-art local feature matching approaches.

show abstract