Learnable Motion Coherence for Correspondence Pruning

11/30/2020
by   Yuan Liu, et al.
3

Motion coherence is an important clue for distinguishing true correspondences from false ones. Modeling motion coherence on sparse putative correspondences is challenging due to their sparsity and uneven distributions. Existing works on motion coherence are sensitive to parameter settings and have difficulty in dealing with complex motion patterns. In this paper, we introduce a network called Laplacian Motion Coherence Network (LMCNet) to learn motion coherence property for correspondence pruning. We propose a novel formulation of fitting coherent motions with a smooth function on a graph of correspondences and show that this formulation allows a closed-form solution by graph Laplacian. This closed-form solution enables us to design a differentiable layer in a learning framework to capture global motion coherence from putative correspondences. The global motion coherence is further combined with local coherence extracted by another local layer to robustly detect inlier correspondences. Experiments demonstrate that LMCNet has superior performances to the state of the art in relative camera pose estimation and correspondences pruning of dynamic scenes.

READ FULL TEXT

page 1

page 4

page 5

page 6

page 7

page 8

research
07/21/2020

Relative Pose Estimation for Multi-Camera Systems from Affine Correspondences

We propose four novel solvers for estimating the relative pose of a mult...
research
10/09/2020

Robust Isometric Non-Rigid Structure-from-Motion

Non-Rigid Structure-from-Motion (NRSfM) reconstructs a deformable 3D obj...
research
07/26/2018

A Minimal Closed-Form Solution for Multi-Perspective Pose Estimation using Points and Lines

We propose a minimal solution for pose estimation using both points and ...
research
08/10/2021

Stroke Correspondence by Labeling Closed Areas

Constructing stroke correspondences between keyframes is one of the most...
research
12/13/2019

Least-squares Optimal Relative Planar Motion for Vehicle-mounted Cameras

A new closed-form solver is proposed minimizing the algebraic error opti...
research
01/03/2021

Consensus-Guided Correspondence Denoising

Correspondence selection between two groups of feature points aims to co...
research
03/28/2023

Learning Second-Order Attentive Context for Efficient Correspondence Pruning

Correspondence pruning aims to search consistent correspondences (inlier...

Please sign up or login with your details

Forgot password? Click here to reset