HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Wed, 28 Oct 2020 17:35:51 GMT
access-control-allow-origin: *
etag: W/"5f99abf7-16e3"
expires: Mon, 29 Dec 2025 05:06:17 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: 9299:2BC55:8494DE:9509E1:695209EF
accept-ranges: bytes
age: 0
date: Mon, 29 Dec 2025 04:56:17 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210026-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1766984177.093856,VS0,VE200
vary: Accept-Encoding
x-fastly-request-id: c9375255874cf721e7a555d2a3f189bc96153fab
content-length: 2148
Dual-Resolution Correspondence Networks
Dual-Resolution Correspondence Networks
1Active Vision Lab & 2Visual Geometry Group
Department of Engineering Science, University of Oxford
|
Abstract
We tackle the problem of establishing dense pixel-wise correspondences between a pair of images. In this work, we introduce Dual-Resolution Correspondence Networks (DualRC-Net), to obtain pixel-wise correspondences in a coarse-to-fine manner. DualRC-Net extracts both coarse- and fine- resolution feature maps. The coarse maps are used to produce a full but coarse 4D correlation tensor, which is then refined by a learnable neighbourhood consensus module. The fine-resolution feature maps are used to obtain the final dense correspondences guided by the refined coarse 4D correlation tensor. The selected coarse-resolution matching scores allow the fine-resolution features to focus only on a limited number of possible matches with high confidence. In this way, DualRC-Net dramatically increases matching reliability and localisation accuracy, while avoiding to apply the expensive 4D convolution kernels on fine-resolution feature maps. We comprehensively evaluate our method on large-scale public benchmarks including HPatches, InLoc, and Aachen Day-Night. It achieves the state-of-the-art results on all of them.
BibTex
@inproceedings{li20dualrc,
author = {Xinghui Li and Kai Han and Shuda Li and Victor Prisacariu},
title = {Dual-Resolution Correspondence Networks},
booktitle = {Conference on Neural Information Processing Systems (NeurIPS)},
year = {2020},
}
Acknowledgments
We gratefully acknowledge the support of the European Commission Project Multiple-actOrs Virtual EmpathicCARegiver for the Elder (MoveCare) and the EPSRC Programme Grant Seebibyte EP/M013774/1.
|
Webpage template borrowed from Split-Brain Autoencoders, CVPR 2017.
