GeoDesc: Learning Local Descriptors by Integrating Geometry Constraints

TL;DR

GeoDesc introduces a novel local descriptor learning method that incorporates multi-view geometry constraints, significantly improving 3D reconstruction accuracy and efficiency in challenging scenarios.

Contribution

The paper presents GeoDesc, a local descriptor that integrates geometry constraints from multi-view reconstructions, enhancing generalization and performance in 3D reconstruction tasks.

Findings

Superior performance on large-scale benchmarks

Effective in challenging reconstruction scenarios

Balances accuracy and efficiency in SfM pipelines

Abstract

Learned local descriptors based on Convolutional Neural Networks (CNNs) have achieved significant improvements on patch-based benchmarks, whereas not having demonstrated strong generalization ability on recent benchmarks of image-based 3D reconstruction. In this paper, we mitigate this limitation by proposing a novel local descriptor learning approach that integrates geometry constraints from multi-view reconstructions, which benefits the learning process in terms of data generation, data sampling and loss computation. We refer to the proposed descriptor as GeoDesc, and demonstrate its superior performance on various large-scale benchmarks, and in particular show its great success on challenging reconstruction tasks. Moreover, we provide guidelines towards practical integration of learned descriptors in Structure-from-Motion (SfM) pipelines, showing the good trade-off that GeoDesc delivers to 3D reconstruction tasks between accuracy and efficiency.