DAC: Detector-Agnostic Spatial Covariances for Deep Local Features

Current deep visual local feature detectors do not model the spatial uncertainty of detected features, producing suboptimal results in downstream applications. In this work, we propose two post-hoc covariance estimates that can be plugged into any pretrained deep feature detector: a simple, isotropi...

Full description

Saved in:
Bibliographic Details
Main Authors: Tirado-Garin, Javier, Warburg, Frederik, Civera, Javier
Format: Conference Proceeding
Language:English
Subjects:
3D Geometry
Bundle adjustment
Codes
Deep Local Features
Detectors
Estimation
Local features
Tensors
Uncertainty
Uncertainty Quantification
Visualization
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Current deep visual local feature detectors do not model the spatial uncertainty of detected features, producing suboptimal results in downstream applications. In this work, we propose two post-hoc covariance estimates that can be plugged into any pretrained deep feature detector: a simple, isotropic estimate that uses the predicted score at a given pixel location, and a full estimate via the local structure tensor of the learned score maps. Both methods are easy to implement and can be applied to any deep feature detector. We show that these covariances are directly related to errors in feature matching, leading to improvements in downstream tasks, including solving the perspective-n-point problem and motion-only bundle adjustment. Code is available at https://github.com/javrtg/DAC.
ISSN:2475-7888
DOI:10.1109/3DV62453.2024.00034