Nr3D contains 41.5K natural, free-form, utterances collected by deploying a 2-player object reference game in 3D scenes. The game is played between two humans: a ‘speaker’ who was asked to describe a designated target object in a ScanNet 3D scene and a ‘listener’ who, given the speaker’s utterance, was asked to select the referred object among its distractors.
@article{achlioptas2020referit_3d,
title={ReferIt3D: Neural Listeners for Fine-Grained 3D Object Identification in Real-World Scenes},
author={Achlioptas, Panos and Abdelreheem, Ahmed and Xia, Fei and Elhoseiny, Mohamed and Guibas, Leonidas},
journal={16th European Conference on Computer Vision (ECCV)},
year={2020}
}
Nr3D contains 41.5K natural, free-form, utterances collected by deploying a 2-player object reference game in 3D scenes. The game is played between two humans: a ‘speaker’ who was asked to describe a designated target object in a ScanNet 3D scene and a ‘listener’ who, given the speaker’s utterance, was asked to select the referred object among its distractors.
Paper Project Code