Pixel-Perfect Structure-from-Motion with Featuremetric Refinement

TLDR: This paper introduces a framework that improves the accuracy of Structure-from-Motion by refining keypoints, camera poses, and 3D points using the direct alignment of deep features. This enables accurate reconstruction at scale in challenging conditions.

---

Abstract

Finding local features that are repeatable across multiple views is a cornerstone of sparse 3D reconstruction. The classical image matching paradigm detects keypoints per-image once and for all, which can yield poorly-localized features and propagate large errors to the final geometry. In this paper, we refine two key steps of structure-from-motion by a direct alignment of low-level image information from multiple views: we first adjust the initial keypoint locations prior to any geometric estimation, and subsequently refine points and camera poses as a post-processing. This refinement is robust to large detection noise and appearance changes, as it optimizes a featuremetric error based on dense features predicted by a neural network. This significantly improves the accuracy of camera poses and scene geometry for a wide range of keypoint detectors, challenging viewing conditions, and off-the-shelf deep features. Our system easily scales to large image collections, enabling pixel-perfect crowd-sourced localization at scale.

BibTeX Citation

@inproceedings{lindenberger2021pixsfm,
  author    = {Philipp Lindenberger and
               Paul-Edouard Sarlin and
               Viktor Larsson and
               Marc Pollefeys},
  title     = {{Pixel-Perfect Structure-from-Motion with Featuremetric Refinement}},
  booktitle = {ICCV},
  year      = {2021},
}