Pixel-Perfect Structure-from-Motion with Featuremetric Refinement
| Autor: | Paul-Edouard Sarlin, Philipp Lindenberger, Viktor Larsson, Marc Pollefeys |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Computational Theory and Mathematics Artificial Intelligence Computer Vision and Pattern Recognition (cs.CV) Applied Mathematics ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Computer Science - Computer Vision and Pattern Recognition Computer Vision and Pattern Recognition Software |
| Popis: | 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. Our code is publicly available at https://github.com/cvg/pixel-perfect-sfm as an add-on to the popular SfM software COLMAP. Accepted to ICCV 2021 for oral presentation |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|