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

arXiv:2309.17175v2 Announce Type: replace
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 …

abstract arxiv concept control cs.cv data fields generators guidance however issue learn prompts representation scale stereotype text type