Abstract:In this work, we explore the challenging task of generating 3D shapes from text. Beyond the existing works, we propose a new approach for text-guided 3D shape generation, capable of producing high-fidelity shapes with colors that match the given text description. This work has several technical contributions. First, we decouple the shape and color predictions for learning features in both texts and shapes, and propose the word-level spatial transformer to correlate word features from text with spatial features from shape. Also, we design a cyclic loss to encourage consistency between text and shape, and introduce the shape IMLE to diversify the generated shapes. Further, we extend the framework to enable text-guided shape manipulation. Extensive experiments on the largest existing text-shape benchmark manifest the superiority of this work. The code and the models are available at this https URL Text-Guided-Shape-Generation.
| Comments: | accepted by CVPR2022 |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2203.14622 [cs.CV] |
| (or arXiv:2203.14622v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2203.14622 arXiv-issued DOI via DataCite |
Submission history
From: Zhengzhe Liu [view email]
[v1]
Mon, 28 Mar 2022 10:20:03 UTC (3,548 KB)