Benchmarking 6DOF Outdoor Visual Localization in Changing Conditions
Torsten Sattler,Will Maddern,Carl Toft,Akihiko Torii,Lars Hammarstrand,Erik Stenborg,Daniel Safari,Daniel Safari,Masatoshi Okutomi,Marc Pollefeys,Marc Pollefeys,Josef Sivic,Fredrik Kahl,Fredrik Kahl,Tomas Pajdla +14 more
- 18 Jun 2018
- pp 8601-8610
TL;DR: This paper introduces the first benchmark datasets specifically designed for analyzing the impact of day-night changes, weather and seasonal variations, as well as sequence-based localization approaches and the need for better local features on visual localization.
read more
Abstract: Visual localization enables autonomous vehicles to navigate in their surroundings and augmented reality applications to link virtual to real worlds. Practical visual localization approaches need to be robust to a wide variety of viewing condition, including day-night changes, as well as weather and seasonal variations, while providing highly accurate 6 degree-of-freedom (6DOF) camera pose estimates. In this paper, we introduce the first benchmark datasets specifically designed for analyzing the impact of such factors on visual localization. Using carefully created ground truth poses for query images taken under a wide variety of conditions, we evaluate the impact of various factors on 6DOF camera pose estimation accuracy through extensive experiments with state-of-the-art localization approaches. Based on our results, we draw conclusions about the difficulty of different conditions, showing that long-term localization is far from solved, and propose promising avenues for future work, including sequence-based localization approaches and the need for better local features. Our benchmark is available at visuallocalization.net.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
•Posted Content
ViewSynth: Learning Local Features from Depth using View Synthesis
TL;DR: It is demonstrated that in the depth modality, ViewSynth outperforms the state-of-the-art depth and RGB local feature extraction techniques in the 3D keypoint matching and camera localization tasks on the RGB-D datasets 7-Scenes, TUM RGBD and CoRBS in most scenarios.
Open Challenges and Conclusion
01 Jan 2022
TL;DR: In this article , the main objective of any loop-closure detection pipeline is to facilitate robust navigation for an extended period and under a broad range of viewing situations, which is the case of our approach.
1
CorrMAE: Pre-training Correspondence Transformers with Masked Autoencoder
Tangfei Liao,Xiaoqin Zhang,Guobao Xiao,Min Li,Tao Wang,Mang Ye +5 more
- 09 Jun 2024
TL;DR: Pre-training correspondence transformers with masked autoencoder (CorrMAE) significantly reduces pre-training cost and improves performance on downstream tasks.
Loop-Closure Detection with 3D LiDAR Data for Extreme Viewpoint Changes
Dimitrios Alexiou,Kosmas Tsiakas,Ioannis Kostavelis,Dimitrios Giakoumis,Antonios Gasteratos,Dimitrios Tzovaras +5 more
- 22 Aug 2022
TL;DR: This paper presents a 3D point cloud-based method for loop closure detection that is tolerant to extreme viewpoint changes, and has been extensively verified on the state-of-art MulRan dataset as well as in a custom-built dataset.
1
Robust and Accurate Cylinder Triangulation
Anna Gummeson,Magnus Oskarsson +1 more
- 05 Dec 2022
TL;DR: In this article , the conic section is constrained to a circle, and algebraic constraints on the dual conic model are given to model this manifold. And a fast minimal solver based on three image silhouette lines is presented to bootstrap robust estimation schemes such as RANSAC.
1
References
•Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
- 04 Sep 2014
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
102.6K
Distinctive Image Features from Scale-Invariant Keypoints
TL;DR: This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.
•Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
- 01 Jan 2015
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
51.9K
Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography
TL;DR: New results are derived on the minimum number of landmarks needed to obtain a solution, and algorithms are presented for computing these minimum-landmark solutions in closed form that provide the basis for an automatic system that can solve the Location Determination Problem under difficult viewing.
A method for registration of 3-D shapes
Paul J. Besl,H.D. McKay +1 more
TL;DR: In this paper, the authors describe a general-purpose representation-independent method for the accurate and computationally efficient registration of 3D shapes including free-form curves and surfaces, based on the iterative closest point (ICP) algorithm, which requires only a procedure to find the closest point on a geometric entity to a given point.
20.6K