Looking at words and points with attention: a benchmark for text-to-shape coherence
(ICCV 2023 Workshop "AI for 3D Content Creation")
Train-val-test splits of GPT2Shape dataset can be found in folder gpt2shape:
Each CSV file contains the ShapeNet model_id of every shape, the corresponding textual description, the name and id of the category and other metadata.
If you find this work useful, please cite our paper:
@InProceedings{Amaduzzi_2023_ICCV,
author = {Amaduzzi, Andrea and Lisanti, Giuseppe and Salti, Samuele and Di Stefano, Luigi},
title = {Looking at Words and Points with Attention: a Benchmark for text-to-Shape Coherence},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops},
month = {October},
year = {2023},
pages = {2868-2877}
}