Amandine Brunetto

I am currently a Ph.D. candidate at PSL Research University, Mines Paris, in the “perception and machine learning” team of the Center for Robotics (CAOR) where I’m adivsed by Pr. Fabien Moutarde.

My research centers on the dynamic intersection of computer vision, audio processing, and neural rendering, with a specific emphasis on multimodal learning that integrates sight and sound information. My objective is to enhance computer vision techniques by enabling them to discern both geometrical and semantic insights from the auditory modality. I also aspire to develop methods that can express spatial understanding through the generation of realistic sounds.

Selected Publications

NeRAF: 3D Scene Infused Neural Radiance and Acoustic Fields

Amandine Brunetto, Sascha Hornauer, and Fabien Moutarde

2024

Bib PDF Code Website

@article{brunetto2024neraf,
  title = {NeRAF: 3D Scene Infused Neural Radiance and Acoustic Fields},
  author = {Brunetto, Amandine and Hornauer, Sascha and Moutarde, Fabien},
  year = {2024},
  eprint = {2405.18213},
  archiveprefix = {arXiv},
}

The Audio-Visual BatVision Dataset for Research on Sight and Sound

Amandine Brunetto, Sascha Hornauer, Stella X. Yu, and Fabien Moutarde

In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2023

Bib PDF Code Website

@inproceedings{brunetto2023batvision,
  author = {Brunetto, Amandine and Hornauer, Sascha and Yu, Stella X. and Moutarde, Fabien},
  booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  title = {The Audio-Visual BatVision Dataset for Research on Sight and Sound},
  year = {2023},
  volume = {},
  number = {},
  pages = {1-8},
  doi = {10.1109/IROS55552.2023.10341715},
}