Pietrantoni Maxime presents Pixel-Perfect Structure-from-Motion with Featuremetric Refinement

On 2022-01-11 11:00:00 at https://feectu.zoom.us/j/98555944426
"Pixel-Perfect Structure-from-Motion with Featuremetric Refinement", Philipp
Lindenberger, Paul-Edouard Sarlin, Viktor Larsson, Marc Pollefeys, ICCV 2021.

Paper URL: https://arxiv.org/abs/2108.08291

Paper abstract: Finding local features that are repeatable across multiple
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
and off-the-shelf deep features. Our system easily scales to large image
collections, enabling pixel-perfect crowd-sourced localization at scale.

See the page of reading groups
Responsible person: Petr Pošík