Abstract
In this paper, we democratise 3D content creation, enabling precise generation of 3D shapes from abstract sketches while overcoming limitations tied to drawing skills. We introduce a novel part-level modelling and alignment framework that facilitates abstraction modelling and cross-modal correspondence. Leveraging the same part-level decoder, our approach seamlessly extends to sketch modelling by establishing correspondence between CLIPasso edgemaps and projected 3D part regions, eliminating the need for a dataset pairing human sketches and 3D shapes. Additionally, our method introduces a seamless in-position editing process as a byproduct of cross-modal part-aligned modelling. Operating in a low-dimensional implicit space, our approach significantly reduces computational demands and processing time.
Citation
@inproceedings{bandyopadhyay2024,
author = {Bandyopadhyay, Hmrishav and Koley, Subhadeep and Das, Ayan
and Kumar Bhunia, Ayan and Sain, Aneeshan and Nath Chowdhury, Pinaki
and Xiang, Tao and Song, Yi-Zhe},
title = {Doodle {Your} {3D:} {From} {Abstract} {Freehand} {Sketches}
to {Precise} {3D} {Shapes}},
booktitle = {Computer Vision \& Pattern Recognition (CVPR) 2024},
date = {2024-02-26},
url = {https://openreview.net/forum?id=R64uFATlbA},
langid = {en}
}