Novel-View Acoustic Synthesis from 3D Reconstructed Rooms
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913468837265408 |
|---|---|
| author | Ahn, Byeongjoo Yang, Karren Hamilton, Brian Sheaffer, Jonathan Ranjan, Anurag Sarabia, Miguel Tuzel, Oncel Chang, Jen-Hao Rick |
| author_facet | Ahn, Byeongjoo Yang, Karren Hamilton, Brian Sheaffer, Jonathan Ranjan, Anurag Sarabia, Miguel Tuzel, Oncel Chang, Jen-Hao Rick |
| contents | We investigate the benefit of combining blind audio recordings with 3D scene information for novel-view acoustic synthesis. Given audio recordings from 2-4 microphones and the 3D geometry and material of a scene containing multiple unknown sound sources, we estimate the sound anywhere in the scene. We identify the main challenges of novel-view acoustic synthesis as sound source localization, separation, and dereverberation. While naively training an end-to-end network fails to produce high-quality results, we show that incorporating room impulse responses (RIRs) derived from 3D reconstructed rooms enables the same network to jointly tackle these tasks. Our method outperforms existing methods designed for the individual tasks, demonstrating its effectiveness at utilizing 3D visual information. In a simulated study on the Matterport3D-NVAS dataset, our model achieves near-perfect accuracy on source localization, a PSNR of 26.44dB and a SDR of 14.23dB for source separation and dereverberation, resulting in a PSNR of 25.55 dB and a SDR of 14.20 dB on novel-view acoustic synthesis. We release our code and model on our project website at https://github.com/apple/ml-nvas3d. Please wear headphones when listening to the results. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_15130 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Novel-View Acoustic Synthesis from 3D Reconstructed Rooms Ahn, Byeongjoo Yang, Karren Hamilton, Brian Sheaffer, Jonathan Ranjan, Anurag Sarabia, Miguel Tuzel, Oncel Chang, Jen-Hao Rick Sound Computer Vision and Pattern Recognition Audio and Speech Processing We investigate the benefit of combining blind audio recordings with 3D scene information for novel-view acoustic synthesis. Given audio recordings from 2-4 microphones and the 3D geometry and material of a scene containing multiple unknown sound sources, we estimate the sound anywhere in the scene. We identify the main challenges of novel-view acoustic synthesis as sound source localization, separation, and dereverberation. While naively training an end-to-end network fails to produce high-quality results, we show that incorporating room impulse responses (RIRs) derived from 3D reconstructed rooms enables the same network to jointly tackle these tasks. Our method outperforms existing methods designed for the individual tasks, demonstrating its effectiveness at utilizing 3D visual information. In a simulated study on the Matterport3D-NVAS dataset, our model achieves near-perfect accuracy on source localization, a PSNR of 26.44dB and a SDR of 14.23dB for source separation and dereverberation, resulting in a PSNR of 25.55 dB and a SDR of 14.20 dB on novel-view acoustic synthesis. We release our code and model on our project website at https://github.com/apple/ml-nvas3d. Please wear headphones when listening to the results. |
| title | Novel-View Acoustic Synthesis from 3D Reconstructed Rooms |
| topic | Sound Computer Vision and Pattern Recognition Audio and Speech Processing |
| url | https://arxiv.org/abs/2310.15130 |