arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2404.07993cs.CV
收藏

连接NeRF、图像与文本

Connecting NeRFs, Images, and Text

University of Bologna(博洛尼亚大学)

Francesco Ballerini, Pierluigi Zama Ramirez, Roberto Mirabella, Samuele Salti, Luigi Di Stefano

AI总结:

本研究探索连接NeRF模态与图像、文本模态的新方向,提出结合NeRF预训练模型与图文多模态模型的框架,学习三者嵌入的双向映射,可实现NeRF零样本分类、图文检索等应用。

摘要:

神经辐射场(Neural Radiance Fields,NeRFs)已成为表示三维场景与物体的标准框架,催生了一种用于信息交换与存储的新型数据类型。与此同时,针对文本与图像数据的多模态表示学习也取得了显著进展。本文探索了一个全新的研究方向,旨在参照图像与文本领域的成熟方法,将NeRF模态与其他模态建立关联。为此,我们提出了一个简洁的框架,该框架结合用于NeRF表示的预训练模型,以及用于文本与图像处理的多模态模型。我们的框架学习NeRF嵌入与对应图像、文本所得嵌入之间的双向映射。这一映射可支撑多种新颖且实用的应用,包括NeRF零样本分类,以及基于图像或文本的NeRF检索。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑