Discovering Details and Scene Structure with Hierarchical Iconoid Shift

Weyand, Tobias; Leibe, Bastian

doi:10.1109/iccv.2013.432

Cited by 20 publications

(11 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A number of image clustering methods based on local features have been introduced [37,38,39]. Due to the spatial verification, the clusters discovered by these methods are reliable.…”

Section: Arxiv:160402426v3 [Cscv] 7 Sep 2016mentioning

confidence: 99%

CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples

Radenović

Tolias

Chum

2016

Lecture Notes in Computer Science

466

566

View full text Add to dashboard Cite

Convolutional Neural Networks (CNNs) achieve state-of-theart performance in many computer vision tasks. However, this achievement is preceded by extreme manual annotation in order to perform either training from scratch or fine-tuning for the target task. In this work, we propose to fine-tune CNN for image retrieval from a large collection of unordered images in a fully automated manner. We employ state-of-the-art retrieval and Structure-from-Motion (SfM) methods to obtain 3D models, which are used to guide the selection of the training data for CNN fine-tuning. We show that both hard positive and hard negative examples enhance the final performance in particular object retrieval with compact codes.

show abstract

“…A number of image clustering methods based on local features have been introduced [37,38,39]. Due to the spatial verification, the clusters discovered by these methods are reliable.…”

Section: Arxiv:160402426v3 [Cscv] 7 Sep 2016mentioning

confidence: 99%

CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples

Radenović

Tolias

Chum

2016

Lecture Notes in Computer Science

466

566

View full text Add to dashboard Cite

show abstract

“…In addition, solving the visual localization problem enables a system to determine the content of a photo. This can be used to develop interesting new applications, e.g., virtual tourism [9] and automatic annotation of photos [10], [11].…”

Section: Introductionmentioning

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

“…A few works addressed the problem of directly identifying or retrieving details, instead of relying on semantic annotation. Weyand and Liebe [13] address the problem of discovering popular details given a large collection of images of a specific building. They presented an offline hierarchical technique capable of finding iconic images at various scales, iteratively solving a medoid shift increasing the kernel bandwidth.…”

Section: Related Workmentioning

confidence: 99%

Wearable Vision for Retrieving Architectural Details in Augmented Tourist Experiences

Alletto

Abati

Serra

et al. 2015

Proceedings of the 7th International Conference on Intelligent Technologies for Interactive Entertainment

View full text Add to dashboard Cite

The interest in cultural cities is in constant growth, and so is the demand for new multimedia tools and applications that enrich their fruition. In this paper we propose an egocentric vision system to enhance tourists' cultural heritage experience. Exploiting a wearable board and a glass-mounted camera, the visitor can retrieve architectural details of the historical building he is observing and receive related multimedia contents. To obtain an effective retrieval procedure we propose a visual descriptor based on the covariance of local features. Differently than the common Bag of Words approaches our feature vector does not rely on a generated visual vocabulary, removing the dependence from a specific dataset and obtaining a reduction of the computational cost. 3D modeling is used to achieve a precise visitor's localization that allows browsing visible relevant details that the user may otherwise miss. Experimental results conducted on a publicly available cultural heritage dataset show that the proposed feature descriptor outperforms Bag of Words techniques

show abstract

Discovering Details and Scene Structure with Hierarchical Iconoid Shift

Cited by 20 publications

References 26 publications

CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples

CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples

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

Wearable Vision for Retrieving Architectural Details in Augmented Tourist Experiences

Contact Info

Product

Resources

About