Connecting NeRFs, Images, and Text

Official code for the paper Connecting NeRFs, Images, and Text, accepted at CVPRW 2024.

[Paper | Project page | Workshop page]

Setup

The code contained in this repository has been tested on Ubuntu 20.04 with Python 3.9.13.

To install the required packages, run:

$ sh requirements.sh

Experiments

The classification, retrieval, and generation directories contain the scripts you need to run in order to replicate our results and a README with some instructions on how to do it.

Datasets

The dataset directory contains the code to create the embedding datasets used in our experiments. If you need access to the original image/text datasets or to the embedding datasets we used, please contact francesco.ballerini4@unibo.it.

Cite us

If you find our work useful, please cite us:

@inproceedings{ballerini2024clip2nerf,
    title = {Connecting {NeRFs}, Images, and Text},
    author = {Ballerini, Francesco 
              and Zama Ramirez, Pierluigi 
              and Mirabella, Roberto  
              and Salti, Samuele
              and Di Stefano, Luigi},
    booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
    year = {2024}
}