10 citations · 16 across the 4 of their papers we have counts for
5 papers
Scaling Cheap Synthetic Pretraining Improves Indoor Radio-Map Prediction
Khoren Petrosyan, Artashes Mkrtchyan, Rafayel Mkrtchyan +2
Real measurements are too limited to train an accurate indoor pathloss predictor that works across a wide range of buildings. Large-scale synthetic pretraining offers a way forward…
Fusion of Pervasive RF Data with Spatial Images via Vision Transformers for Enhanced Mapping in Smart Cities
Rafayel Mkrtchyan, Armen Manukyan, Hrant Khachatrian +1
In this paper, we present a deep learning-based approach that integrates the DINOv2 architecture to improve building mapping by combining (possibly erroneous) maps from open-source…
Vision Transformers for Efficient Indoor Pathloss Radio Map Prediction
Rafayel Mkrtchyan, Edvard Ghukasyan, Khoren Petrosyan +2
Indoor pathloss prediction is a fundamental task in wireless network planning, yet it remains challenging due to environmental complexity and data scarcity. In this work, we propos…
Outdoor Environment Reconstruction with Deep Learning on Radio Propagation Paths
Hrant Khachatrian, Rafayel Mkrtchyan, Theofanis P. Raptis
Conventional methods for outdoor environment reconstruction rely predominantly on vision-based techniques like photogrammetry and LiDAR, facing limitations such as constrained cove…
ML-based Approaches for Wireless NLOS Localization: Input Representations and Uncertainty Estimation
Rafayel Darbinyan, Hrant Khachatrian, Rafayel Mkrtchyan +1
The challenging problem of non-line-of-sight (NLOS) localization is critical for many wireless networking applications. The lack of available datasets has made NLOS localization di…