Connecting NeRFs, Images, and Text
This work addresses the challenge of integrating NeRFs into multimodal systems for researchers and practitioners in 3D scene representation and AI.
The paper tackles the problem of connecting Neural Radiance Fields (NeRFs) with images and text by proposing a framework that learns bidirectional mappings between their embeddings, enabling applications like NeRF zero-shot classification and retrieval.
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 exploits pre-trained models for NeRF representations alongside multimodal models for text and image processing. Our framework learns a bidirectional mapping between NeRF embeddings and those obtained from corresponding images and text. This mapping unlocks several novel and useful applications, including NeRF zero-shot classification and NeRF retrieval from images or text.