Visual Correspondence Hallucination: Towards Geometric Reasoning

06/17/2021
by   Hugo Germain, et al.
0

Given a pair of partially overlapping source and target images and a keypoint in the source image, the keypoint's correspondent in the target image can be either visible, occluded or outside the field of view. Local feature matching methods are only able to identify the correspondent's location when it is visible, while humans can also hallucinate its location when it is occluded or outside the field of view through geometric reasoning. In this paper, we bridge this gap by training a network to output a peaked probability distribution over the correspondent's location, regardless of this correspondent being visible, occluded, or outside the field of view. We experimentally demonstrate that this network is indeed able to hallucinate correspondences on unseen pairs of images. We also apply this network to a camera pose estimation problem and find it is significantly more robust than state-of-the-art local feature matching-based competitors.

READ FULL TEXT

page 4

page 5

page 8

page 10

page 11

page 12

page 21

page 22

research
03/30/2016

Learning Local Descriptors by Optimizing the Keypoint-Correspondence Criterion

Current best local descriptors are learned on a large dataset of matchin...
research
09/13/2021

Pose with Style: Detail-Preserving Pose-Guided Image Synthesis with Conditional StyleGAN

We present an algorithm for re-rendering a person from a single image un...
research
09/03/2018

Object Pose Estimation from Monocular Image using Multi-View Keypoint Correspondence

Understanding the geometry and pose of objects in 2D images is a fundame...
research
06/16/2022

Virtual Correspondence: Humans as a Cue for Extreme-View Geometry

Recovering the spatial layout of the cameras and the geometry of the sce...
research
04/01/2020

Pose-guided Visible Part Matching for Occluded Person ReID

Occluded person re-identification is a challenging task as the appearanc...
research
09/29/2020

CoKe: Localized Contrastive Learning for Robust Keypoint Detection

Today's most popular approaches to keypoint detection learn a holistic r...
research
04/12/2023

TopTrack: Tracking Objects By Their Top

In recent years, the joint detection-and-tracking paradigm has been a ve...

Please sign up or login with your details

Forgot password? Click here to reset