TextField3D: Towards Enhancing Open-Vocabulary 3D Generation with Noisy Text Fields

Tianyu Huang, Yihan Zeng, Bowen Dong, Hang Xu, Songcen Xu, Rynson W. H. Lau, Wangmeng Zuo

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: 3D Open Vocabulary, Conditional Generation

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

Abstract: Recent works learn 3D representation explicitly under text-3D guidance. However, limited text-3D data restricts the vocabulary scale and text control of generations. Generators may easily fall into a stereotype concept for certain text prompts, thus losing open-vocabulary generation ability. To tackle this issue, we introduce a conditional 3D generative model, namely TextField3D. Specifically, rather than using the text prompts as input directly, we suggest to inject dynamic noise into the latent space of given text prompts, i.e., Noisy Text Fields (NTFs). In this way, limited 3D data can be mapped to the appropriate range of textual latent space that is expanded by NTFs. To this end, an NTFGen module is proposed to model general text latent code in noisy fields. Meanwhile, an NTFBind module is proposed to align view-invariant image latent code to noisy fields, further supporting image-conditional 3D generation. To guide the conditional generation in both geometry and texture, multi-modal discrimination is constructed with a text-3D discriminator and a text-2.5D discriminator. Compared to previous methods, TextField3D includes three merits: 1) large vocabulary, 2) text consistency, and 3) low latency. Extensive experiments demonstrate that our method achieves a potential open-vocabulary 3D generation capability.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Primary Area: generative models

Submission Number: 5579