Structure-from-Motion using Dense CNN Features with Keypoint Relocalization

TL;DR

This paper introduces a novel SfM pipeline that leverages dense CNN features with keypoint relocalization to achieve pixel-level accuracy, significantly improving reconstruction in challenging scenarios with appearance changes.

Contribution

The proposed method combines dense CNN features with a relocalization technique to enhance SfM accuracy and robustness against appearance variations.

Findings

Outperforms COLMAP with RootSIFT on Aachen Day-Night dataset

Achieves pixel-level feature correspondence accuracy

Demonstrates improved reconstruction in challenging conditions

Abstract

Structure from Motion (SfM) using imagery that involves extreme appearance changes is yet a challenging task due to a loss of feature repeatability. Using feature correspondences obtained by matching densely extracted convolutional neural network (CNN) features significantly improves the SfM reconstruction capability. However, the reconstruction accuracy is limited by the spatial resolution of the extracted CNN features which is not even pixel-level accuracy in the existing approach. Providing dense feature matches with precise keypoint positions is not trivial because of memory limitation and computational burden of dense features. To achieve accurate SfM reconstruction with highly repeatable dense features, we propose an SfM pipeline that uses dense CNN features with relocalization of keypoint position that can efficiently and accurately provide pixel-level feature correspondences. Then, we demonstrate on the Aachen Day-Night dataset that the proposed SfM using dense CNN features with the keypoint relocalization outperforms a state-of-the-art SfM (COLMAP using RootSIFT) by a large margin.