Consensus-Guided Correspondence Denoising

01/03/2021
by   Chen Zhao, et al.
2

Correspondence selection between two groups of feature points aims to correctly recognize the consistent matches (inliers) from the initial noisy matches. The selection is generally challenging since the initial matches are generally extremely unbalanced, where outliers can easily dominate. Moreover, random distributions of outliers lead to the limited robustness of previous works when applied to different scenarios. To address this issue, we propose to denoise correspondences with a local-to-global consensus learning framework to robustly identify correspondence. A novel "pruning" block is introduced to distill reliable candidates from initial matches according to their consensus scores estimated by dynamic graphs from local to global regions. The proposed correspondence denoising is progressively achieved by stacking multiple pruning blocks sequentially. Our method outperforms state-of-the-arts on robust line fitting, wide-baseline image matching and image localization benchmarks by noticeable margins and shows promising generalization capability on different distributions of initial matches.

READ FULL TEXT

page 12

page 13

page 14

08/23/2017

In search of inliers: 3d correspondence by local and global voting

We present a method for finding correspondence between 3D models. From a...
04/30/2019

Comparative evaluation of 2D feature correspondence selection algorithms

Correspondence selection aiming at seeking correct feature correspondenc...
03/25/2021

COTR: Correspondence Transformer for Matching Across Images

We propose a novel framework for finding correspondences in images based...
12/03/2020

Patch2Pix: Epipolar-Guided Pixel-Level Correspondences

Deep learning has been applied to a classical matching pipeline which ty...
11/30/2020

Learnable Motion Coherence for Correspondence Pruning

Motion coherence is an important clue for distinguishing true correspond...
11/21/2011

Distributed Multi-view Matching in Networks with Limited Communications

We address the problem of distributed matching of features in networks w...
04/22/2020

Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutions

In this work we target the problem of estimating accurately localised co...