Radio-assisted image inpainting

PhD Position – Thesis offer M/F (Reference: SN/JLD/PHD/Converge/092023)

Wireless communications and computer vision have evolved as separate scientific areas. However, with the advent of new sensor technologies and AI-based signal processing algorithms in both telecommunication and computer vision, new joint studies are now possible [1]. For examples, wireless communications could benefit from visual data to prevent blockage whereas computer vision could gain robustness against occlusions if helped by radio-based imaging.

Within the context of a new European project converge whose motto is "communicate to see and see to communicate", EURECOM proposes a PhD position to work on "radio assisted image inpainting" [2]. The objective is to guess what a camera cannot see because of partial (e.g. an object) or total (e.g. wall [3]) occlusions thanks to existing radio/wireless waves attached to WiFi and or 4/5G signals present in the same space. In the opposite way, computer vision can allow to see obstacles that can create problems in the propagation of radio waves [4].

[1] Nishio, T., Koda, Y., Park, J., Bennis, M., & Doppler, K. (2021). When wireless communications meet computer vision in beyond 5G. IEEE Communications Standards Magazine, 5(2), 76-83.
[2] Hanyu Xiang, Qin Zou, Muhammad Ali Nawaz, Xianfeng Huang, Fan Zhang, Hongkai Yu, Deep learning for image inpainting: A survey, Pattern Recognition, Volume 134, 2023.
[3]  Fadel Adib and Dina Katabi. 2013. See through walls with WiFi!. SIGCOMM Comput. Commun. Rev. 43, 4 (August 2013), 75-86. DOI:
[4] Charan, G., Alrabeiah, M., & Alkhateeb, A. (2021). Vision-aided 6G wireless communications: Blockage prediction and proactive handoff. IEEE Transactions on Vehicular Technology, 70(10), 10193-10208.


  • Education Level / Degree : Master
  • Field / specialty: Signal & Image processing / Artificial Intelligence / Communications

The application must include:

  • Detailed curriculum,
  • Name and address of 2 references.

Applications should be submitted by e-mail to with the reference: SN/JLD/PHD/Converge/092023

Start date: 01/09/2023
Duration: Duration of the thesis