Saved in:
Bibliographic Details
Main Authors: Pyatov, Vladislav, Koshelev, Iaroslav, Lefkimmiatis, Stamatis
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.17983
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909360642326528
author Pyatov, Vladislav
Koshelev, Iaroslav
Lefkimmiatis, Stamatis
author_facet Pyatov, Vladislav
Koshelev, Iaroslav
Lefkimmiatis, Stamatis
contents We present a novel two-view geometry estimation framework which is based on a differentiable robust loss function fitting. We propose to treat the robust fundamental matrix estimation as an implicit layer, which allows us to avoid backpropagation through time and significantly improves the numerical stability. To take full advantage of the information from the feature matching stage we incorporate learnable weights that depend on the matching confidences. In this way our solution brings together feature extraction, matching and two-view geometry estimation in a unified end-to-end trainable pipeline. We evaluate our approach on the camera pose estimation task in both outdoor and indoor scenarios. The experiments on several datasets show that the proposed method outperforms both classic and learning-based state-of-the-art methods by a large margin. The project webpage is available at: https://github.com/VladPyatov/ihls
format Preprint
id arxiv_https___arxiv_org_abs_2410_17983
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Robust Two-View Geometry Estimation with Implicit Differentiation
Pyatov, Vladislav
Koshelev, Iaroslav
Lefkimmiatis, Stamatis
Computer Vision and Pattern Recognition
Robotics
We present a novel two-view geometry estimation framework which is based on a differentiable robust loss function fitting. We propose to treat the robust fundamental matrix estimation as an implicit layer, which allows us to avoid backpropagation through time and significantly improves the numerical stability. To take full advantage of the information from the feature matching stage we incorporate learnable weights that depend on the matching confidences. In this way our solution brings together feature extraction, matching and two-view geometry estimation in a unified end-to-end trainable pipeline. We evaluate our approach on the camera pose estimation task in both outdoor and indoor scenarios. The experiments on several datasets show that the proposed method outperforms both classic and learning-based state-of-the-art methods by a large margin. The project webpage is available at: https://github.com/VladPyatov/ihls
title Robust Two-View Geometry Estimation with Implicit Differentiation
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2410.17983