Key. net: Keypoint detection by handcrafted and learned cnn filters revisited

A Barroso-Laguna, K Mikolajczyk - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
We introduce a novel approach for keypoint detection that combines handcrafted and
learned CNN filters within a shallow multi-scale architecture. Handcrafted filters provide …

Segloc: Learning segmentation-based representations for privacy-preserving visual localization

M Pietrantoni, M Humenberger… - Proceedings of the …, 2023 - openaccess.thecvf.com
Inspired by properties of semantic segmentation, in this paper we investigate how to
leverage robust image segmentation in the context of privacy-preserving visual localization …

Ninjadesc: Content-concealing visual descriptors via adversarial learning

T Ng, HJ Kim, VT Lee, D DeTone… - Proceedings of the …, 2022 - openaccess.thecvf.com
In the light of recent analyses on privacy-concerning scene revelation from visual
descriptors, we develop descriptors that conceal the input image content. In particular, we …

Privacy-preserving representations are not enough: Recovering scene content from camera poses

K Chelani, T Sattler, F Kahl… - Proceedings of the …, 2023 - openaccess.thecvf.com
Visual localization is the task of estimating the camera pose from which a given image was
taken and is central to several 3D computer vision applications. With the rapid growth in the …

Ps-fedgan: An efficient federated learning framework based on partially shared generative adversarial networks for data privacy

A Wijesinghe, S Zhang, Z Ding - arXiv preprint arXiv:2305.11437, 2023 - arxiv.org
Federated Learning (FL) has emerged as an effective learning paradigm for distributed
computation owing to its strong potential in capturing underlying data statistics while …

UFed-GAN: A Secure Federated Learning Framework with Constrained Computation and Unlabeled Data

A Wijesinghe, S Zhang, S Qi, Z Ding - arXiv preprint arXiv:2308.05870, 2023 - arxiv.org
To satisfy the broad applications and insatiable hunger for deploying low latency multimedia
data classification and data privacy in a cloud-based setting, federated learning (FL) has …

PS-FedGAN: An Efficient Federated Learning Framework with Strong Data Privacy

A Wijesinghe, S Zhang, Z Ding - IEEE Internet of Things Journal, 2024 - ieeexplore.ieee.org
Federated Learning (FL) has emerged as an effective paradigm for distributed learning
systems owing to its strong potential in exploiting underlying data characteristics while …

Verifiable access control for augmented reality localization and mapping

S Zhu, HJ Kim, M Monge, GE Suh, A Alaghi… - arXiv preprint arXiv …, 2022 - arxiv.org
Localization and mapping is a key technology for bridging the virtual and physical worlds in
augmented reality (AR). Localization and mapping works by creating and querying maps …

Obfuscation Based Privacy Preserving Representations are Recoverable Using Neighborhood Information

K Chelani, A Benbihi, F Kahl, T Sattler… - arXiv preprint arXiv …, 2024 - arxiv.org
Rapid growth in the popularity of AR/VR/MR applications and cloud-based visual
localization systems has given rise to an increased focus on the privacy of user content in …

UFed-GAN: Secure Federated Learning over Wireless Sensor Networks with Unlabeled Data

A Wijesinghe, S Zhang, S Qi… - 2024 IEEE International …, 2024 - ieeexplore.ieee.org
The rising demand for deploying low-latency data analysis and protecting privacy in a cloud-
based setting has led to the emergence of federated learning (FL) as an important learning …