-
[pdf]
[supp]
[bibtex]@InProceedings{Taioli_2023_ICCV, author = {Taioli, Francesco and Cunico, Federico and Girella, Federico and Bologna, Riccardo and Farinelli, Alessandro and Cristani, Marco}, title = {Language-Enhanced RNR-Map: Querying Renderable Neural Radiance Field Maps with Natural Language}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2023}, pages = {4669-4674} }
Language-Enhanced RNR-Map: Querying Renderable Neural Radiance Field Maps with Natural Language
Abstract
We present Le-RNR-Map, a Language-enhanced Renderable Neural Radiance map for Visual Navigation with natural language query prompts. The recently proposed RNR-Map employs a grid structure comprising latent codes positioned at each pixel. These latent codes, which are derived from image observation, enable: i) image rendering given a camera pose, since they are converted to Neural Radiance Field; ii) image navigation and localization with astonishing accuracy. On top of this, we enhance RNR-Map with CLIP-based embedding latent codes, allowing natural language search without additional label data. We evaluate the effectiveness of this map in single and multi-object searches. We also investigate its compatibility with a Large Language Model as an "affordance query resolver". Code and videos are available at the link https://intelligolabs.github.io/Le-RNR-Map/
Related Material