CLIP-Sculptor: Zero-Shot Generation of High-Fidelity and Diverse Shapes From Natural Language

Aditya Sanghi, Rao Fu, Vivian Liu, Karl D.D. Willis, Hooman Shayani, Amir H. Khasahmadi, Srinath Sridhar, Daniel Ritchie; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, pp. 18339-18348

Abstract


Recent works have demonstrated that natural language can be used to generate and edit 3D shapes. However, these methods generate shapes with limited fidelity and diversity. We introduce CLIP-Sculptor, a method to address these constraints by producing high-fidelity and diverse 3D shapes without the need for (text, shape) pairs during training. CLIP-Sculptor achieves this in a multi-resolution approach that first generates in a low-dimensional latent space and then upscales to a higher resolution for improved shape fidelity. For improved shape diversity, we use a discrete latent space which is modeled using a transformer conditioned on CLIP's image-text embedding space. We also present a novel variant of classifier-free guidance, which improves the accuracy-diversity trade-off. Finally, we perform extensive experiments demonstrating that CLIP-Sculptor outperforms state-of-the-art baselines.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Sanghi_2023_CVPR, author = {Sanghi, Aditya and Fu, Rao and Liu, Vivian and Willis, Karl D.D. and Shayani, Hooman and Khasahmadi, Amir H. and Sridhar, Srinath and Ritchie, Daniel}, title = {CLIP-Sculptor: Zero-Shot Generation of High-Fidelity and Diverse Shapes From Natural Language}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18339-18348} }