SIP2Net: Situational-Aware Indoor Pathloss-Map Prediction Network for Radio Map Generation
This paper presents our indoor pathloss prediction solution to ICASSP 2025 Signal Process Grand Challenge: First Indoor Path Loss Prediction Challenge. The proposed U-Net-based network incorporates dedicated asymmetric convolutions and spatial pyramid pooling to enhance reconstruction quality. Our approach achieves a weighted root mean squared error (RMSE) of 9.411 dB on the final test set, securing the 1st place in the challenge.
Authors
- Ziyi Lu (ORCID: https://orcid.org/0000-0002-8209-3188)
- Wencheng Lu
- Shijian Gao (ORCID: https://orcid.org/0000-0002-8105-7927)
- Yan Jia (ORCID: https://orcid.org/0000-0002-1233-1507)
Publication Details
- Published
- 2025-03-12
- DOI
- https://doi.org/10.1109/icassp49660.2025.10890319
- Citations
- 4
- Primary Topic
- Indoor and Outdoor Localization Technologies
- Type
- article
- Field-Weighted Citation Impact
- 2.92