Patch2Pix: Epipolar-Guided Pixel-Level Correspondences

12/03/2020
by   Qunjie Zhou, et al.
5

Deep learning has been applied to a classical matching pipeline which typically involves three steps: (i) local feature detection and description, (ii) feature matching, and (iii) outlier rejection. Recently emerged correspondence networks propose to perform those steps inside a single network but suffer from low matching resolution due to the memory bottleneck. In this work, we propose a new perspective to estimate correspondences in a detect-to-refine manner, where we first predict patch-level match proposals and then refine them. We present a novel refinement network Patch2Pix that refines match proposals by regressing pixel-level matches from the local regions defined by those proposals and jointly rejecting outlier matches with confidence scores, which is weakly supervised to learn correspondences that are consistent with the epipolar geometry of an input image pair. We show that our refinement network significantly improves the performance of correspondence networks on image matching, homography estimation, and localization tasks. In addition, we show that our learned refinement generalizes to fully-supervised methods without re-training, which leads us to state-of-the-art localization performance.

READ FULL TEXT

page 12

page 13

page 14

page 15

research
12/08/2022

DDM-NET: End-to-end learning of keypoint feature Detection, Description and Matching for 3D localization

In this paper, we propose an end-to-end framework that jointly learns ke...
research
08/06/2023

Local Consensus Enhanced Siamese Network with Reciprocal Loss for Two-view Correspondence Learning

Recent studies of two-view correspondence learning usually establish an ...
research
09/25/2022

ECO-TR: Efficient Correspondences Finding Via Coarse-to-Fine Refinement

Modeling sparse and dense image matching within a unified functional cor...
research
05/23/2022

TransforMatcher: Match-to-Match Attention for Semantic Correspondence

Establishing correspondences between images remains a challenging task, ...
research
09/06/2021

The Animation Transformer: Visual Correspondence via Segment Matching

Visual correspondence is a fundamental building block on the way to buil...
research
11/21/2011

Distributed Multi-view Matching in Networks with Limited Communications

We address the problem of distributed matching of features in networks w...
research
01/03/2021

Consensus-Guided Correspondence Denoising

Correspondence selection between two groups of feature points aims to co...

Please sign up or login with your details

Forgot password? Click here to reset