CPlaNet: Enhancing Image Geolocalization by Combinatorial Partitioning of Maps

Seo, Paul Hongsuck; Weyand, Tobias; Sim, Jack; Han, Bohyung

doi:10.1007/978-3-030-01249-6_33

Cited by 45 publications

(26 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another approach is to model visual localization as a classification task [17], [46], [47]. Such methods subdivide a scene into individual places and then learn classifiers, e.g., based on a BoW representation [17], [46] or using CNNs [47], [48], to distinguish between images belonging to different places.…”

Section: Related Workmentioning

confidence: 99%

Are Large-Scale 3D Models Really Necessary for Accurate Visual Localization?

Torii

Taira

Šivic

et al. 2021

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

Accurate visual localization is a key technology for autonomous navigation. 3D structure-based methods employ 3D models of the scene to estimate the full 6 degree-of-freedom (DOF) pose of a camera very accurately. However, constructing (and extending) large-scale 3D models is still a significant challenge. In contrast, 2D image retrieval-based methods only require a database of geo-tagged images, which is trivial to construct and to maintain. They are often considered inaccurate since they only approximate the positions of the cameras. Yet, the exact camera pose can theoretically be recovered when enough relevant database images are retrieved. In this paper, we demonstrate experimentally that large-scale 3D models are not strictly necessary for accurate visual localization. We create reference poses for a large and challenging urban dataset. Using these poses, we show that combining image-based methods with local reconstructions results in a higher pose accuracy compared to state-of-the-art structure-based methods, albeight at higher run-time costs. We show that some of these run-time costs can be alleviated by exploiting known database image poses. Our results suggest that we might want to reconsider the need for large-scale 3D models in favor of more local models, but also that further research is necessary to accelerate the local reconstruction process.

show abstract

Section: Related Workmentioning

confidence: 99%

Are Large-Scale 3D Models Really Necessary for Accurate Visual Localization?

Torii

Taira

Šivic

et al. 2021

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

show abstract

“…The latter two definitions give the flexibility to set the error threshold, adapting it to the use-case. For example, the GPS error may be set differently for recognition on street level or city level [238].…”

Section: B Evaluation Of Resultsmentioning

confidence: 99%

“…The most common metric applied to both retrieval-based and classificationbased methods is the fraction of correctly recognized queries. This metric is indicated with different names, such as accuracy [238] or recall (in this context with a slight different meaning than in pure image retrieval) [69], [121]. Another quantity of interest in the metric is the number of hypotheses that are considered to verify a query, i.e., the number of top ranked retrieved images or most likely classes.…”

Section: B Evaluation Of Resultsmentioning

confidence: 99%

See 1 more Smart Citation

A Survey on Deep Visual Place Recognition

2021

View full text Add to dashboard Cite

In recent years visual place recognition (VPR), i.e., the problem of recognizing the location of images, has received considerable attention from multiple research communities, spanning from computer vision to robotics and even machine learning. This interest is fueled on one hand by the relevance that visual place recognition holds for many applications and on the other hand by the unsolved challenge of making these methods perform reliably in different conditions and environments. This paper presents a survey of the state-of-the-art of research on visual place recognition, focusing on how it has been shaped by the recent advances in deep learning. We start discussing the image representations used in this task and how they have evolved from using hand-crafted to deep-learned features. We further review how metric learning techniques are used to get more discriminative representations, as well as techniques for dealing with occlusions, distractors, and shifts in the visual domain of the images. The survey also provides an overview of the specific solutions that have been proposed for applications in robotics and with aerial imagery. Finally the survey provides a summary of datasets that are used in visual place recognition, highlighting their different characteristics. INDEX TERMS Visual place recognition, image representation learning, deep learning.

show abstract

“…While they are effective, we will show that our SARE objective outperforms them in the IBL task later. Three interesting exceptions which do not use triplet or contrastive embedding objective are the planet [42], IM2GPS-CNN [40], and CPlaNet [34]. They formulate IBL as a geographic position classification task.…”

Section: Related Workmentioning

confidence: 99%

Stochastic Attraction-Repulsion Embedding for Large Scale Image Localization

Liu

Dai

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

100

124

View full text Add to dashboard Cite

This paper tackles the problem of large-scale imagebased localization (IBL) where the spatial location of a query image is determined by finding out the most similar reference images in a large database. For solving this problem, a critical task is to learn discriminative image representation that captures informative information relevant for localization. We propose a novel representation learning method having higher location-discriminating power.It provides the following contributions: 1) we represent a place (location) as a set of exemplar images depicting the same landmarks and aim to maximize similarities among intra-place images while minimizing similarities among inter-place images; 2) we model a similarity measure as a probability distribution on L 2 -metric distances between intra-place and inter-place image representations; 3) we propose a new Stochastic Attraction and Repulsion Embedding (SARE) loss function minimizing the KL divergence between the learned and the actual probability distributions; 4) we give theoretical comparisons between SARE, triplet ranking [2] and contrastive losses [25]. It provides insights into why SARE is better by analyzing gradients.Our SARE loss is easy to implement and pluggable to any CNN. Experiments show that our proposed method improves the localization performance on standard benchmarks by a large margin. Demonstrating the broad applicability of our method, we obtained the 3 rd place out of 209 teams in the 2018 Google Landmark Retrieval Challenge [1]. Our code and model are available at https: //github.com/Liumouliu/deepIBL. arXiv:1808.08779v2 [cs.CV] 6 Aug 2019 0 5 10 15 20 25 N-Number of top retrieved database images 86 88 90 92 94 96 98 100 Recall@N(%) Gaussian-Ind. Gaussian-Joint Cauchy-Ind. Cauchy-Joint Exponential-Ind. Exponential-Joint 0 5 10 15 20 25 N-Number of top retrieved database images 94 95 96 97 98 99 Recall@N(%) Gaussian-Ind. Gaussian-Joint Cauchy-Ind. Cauchy-Joint Exponential-Ind. Exponential-Joint 0 5 10 15 20 25 N-Number of top retrieved database images 75 80 85 90 95 Recall@N(%) Gaussian-Ind. Gaussian-Joint Cauchy-Ind. Cauchy-Joint Exponential-Ind. Exponential-Joint 0 5 10 15 20 25 N-Number of top retrieved database images 76 78 80 82 84 86 88 90 92 Recall@N(%) Gaussian-Ind. Gaussian-Joint Cauchy-Ind. Cauchy-Joint Exponential-Ind. Exponential-Joint

show abstract

CPlaNet: Enhancing Image Geolocalization by Combinatorial Partitioning of Maps

Cited by 45 publications

References 46 publications

Are Large-Scale 3D Models Really Necessary for Accurate Visual Localization?

Are Large-Scale 3D Models Really Necessary for Accurate Visual Localization?

A Survey on Deep Visual Place Recognition

Stochastic Attraction-Repulsion Embedding for Large Scale Image Localization

Contact Info

Product

Resources

About