Downloads · 30 days
0
NeRAF
AmandineBtto/NeRAF
NeRAF is a machine learning model from AmandineBtto. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as cc-by-nc-sa-4.0.
Official pretrained model weights for NeRAF from the paper: "NeRAF: 3D Scene Infused Neural Radiance and Acoustic Fields" (ICLR 2025).
Access
Public
Updated Mar 11, 2026
Repo size
7.5 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.ckpt7.5 GB · 100%
At a glance
- License
- cc-by-nc-sa-4.0
- Access
- Public
- Created
- Mar 11, 2026
- Updated
- Mar 11, 2026
- SHA
- e15e6573
Datasets
Model card
From the Hugging Face model README
Official pretrained model weights for NeRAF from the paper: "NeRAF: 3D Scene Infused Neural Radiance and Acoustic Fields" (ICLR 2025).
This repository contains pretrained checkpoints for RAF dataset and 6 SoundSpaces scenes.
For training, evaluation, and usage instructions please see the official codebase: 👉 https://github.com/AmandineBtto/NeRAF
You can download all weights using:
huggingface-cli download AmandineBtto/NeRAF --local-dir weights/NeRAF
If you use these weights, please cite:
@inproceedings{
brunetto2025neraf,
title={Ne{RAF}: 3D Scene Infused Neural Radiance and Acoustic Fields},
author={Amandine Brunetto and Sascha Hornauer and Fabien Moutarde},
booktitle={The Thirteenth International Conference on Learning Representations},
year={2025},
url={https://openreview.net/forum?id=njvSBvtiwp}
}
- License
- cc-by-nc-sa-4.0
- Created
- Mar 11, 2026
- Updated
- Mar 11, 2026