Connecting NeRFs, Images, and Text

arXiv:2404.07993v1 Announce Type: new
Abstract: Neural Radiance Fields (NeRFs) have emerged as a standard framework for representing 3D scenes and objects, introducing a novel data type for information exchange and storage. Concurrently, significant progress has been made in multimodal representation learning for text and image data. This paper explores a novel research direction that aims to connect the NeRF modality with other modalities, similar to established methodologies for images and text. To this end, we propose a simple framework that …

3d scenes abstract arxiv cs.cv data fields framework image image data images information multimodal neural radiance fields novel objects paper progress representation representation learning research standard storage text type