Visual Correspondence Hallucination

TL;DR

This paper introduces a neural network that predicts the location of a keypoint's correspondence in a target image, even when it is occluded or outside the field of view, improving robustness in camera pose estimation.

Contribution

It presents a novel network trained to hallucinate correspondences regardless of visibility, bridging the gap between human reasoning and local feature matching methods.

Findings

Network successfully hallucinated correspondences in unseen scenes.

Method outperformed state-of-the-art local feature matching in camera pose estimation.

Demonstrated robustness to occlusions and out-of-view keypoints.

Abstract

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 pairs of images captured in scenes that were not seen at training-time. We also apply this network to an absolute camera pose estimation problem and find it is significantly more robust than state-of-the-art local feature matching-based competitors.