# Online Embedding Multi-Scale CLIP Features into 3D Maps

arXiv: https://arxiv.org/abs/2403.18178 · HTML: https://mlsanity.com/paper/2403.18178/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 30 references that are in the map.
- First posted on arXiv 27 Mar 2024.

## Builds on (most cited first, 25 of 25)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding](https://mlsanity.com/paper/2104.12763/) (2021)
- [Language-driven Semantic Segmentation](https://mlsanity.com/paper/2201.03546/) (2022)
- [DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras](https://mlsanity.com/paper/2108.10869/) (2021)
- [Detecting Twenty-thousand Classes using Image-level Supervision](https://mlsanity.com/paper/2201.02605/) (2022)
- [OpenScene: 3D Scene Understanding with Open Vocabularies](https://mlsanity.com/paper/2211.15654/) (2022)
- [LERF: Language Embedded Radiance Fields](https://mlsanity.com/paper/2303.09553/) (2023)
- [Habitat 2.0: Training Home Assistants to Rearrange their Habitat](https://mlsanity.com/paper/2106.14405/) (2021)
- [LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action](https://mlsanity.com/paper/2207.04429/) (2022)
- [Object Goal Navigation using Goal-Oriented Semantic Exploration](https://mlsanity.com/paper/2007.00643/) (2020)
- [Visual Language Maps for Robot Navigation](https://mlsanity.com/paper/2210.05714/) (2022)
- [VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigation](https://mlsanity.com/paper/2312.03275/) (2023)
- [CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigation](https://mlsanity.com/paper/2203.10421/) (2022)
- [Simple but Effective: CLIP Embeddings for Embodied AI](https://mlsanity.com/paper/2111.09888/) (2021)
- [ZSON: Zero-Shot Object-Goal Navigation using Multimodal Goal Embeddings](https://mlsanity.com/paper/2206.12403/) (2022)
- [SemanticFusion: Dense 3D Semantic Mapping with Convolutional Neural Networks](https://mlsanity.com/paper/1609.05130/) (2016)
- [Fusion++: Volumetric Object-Level SLAM](https://mlsanity.com/paper/1808.08378/) (2018)
- [MaskFusion: Real-Time Recognition, Tracking and Reconstruction of Multiple Moving Objects](https://mlsanity.com/paper/1804.09194/) (2018)
- [MID-Fusion: Octree-based Object-Level Multi-Instance Dynamic SLAM](https://mlsanity.com/paper/1812.07976/) (2018)
- [Spatio-Temporal Graph Localization Networks for Image-based Navigation](https://mlsanity.com/paper/2204.13237/) (2022)
- [Language to Map: Topological map generation from natural language path instructions](https://mlsanity.com/paper/2403.10008/) (2024)

## Abstract (arXiv)

This study introduces a novel approach to online embedding of multi-scale CLIP (Contrastive Language-Image Pre-Training) features into 3D maps. By harnessing CLIP, this methodology surpasses the constraints of conventional vocabulary-limited methods and enables the incorporation of semantic information into the resultant maps. While recent approaches have explored the embedding of multi-modal features in maps, they often impose significant computational costs, lacking practicality for exploring unfamiliar environments in real time. Our approach tackles these challenges by efficiently computing and embedding multi-scale CLIP features, thereby facilitating the exploration of unfamiliar environments through real-time map generation. Moreover, the embedding CLIP features into the resultant maps makes offline retrieval via linguistic queries feasible. In essence, our approach simultaneously achieves real-time object search and mapping of unfamiliar environments. Additionally, we propose a zero-shot object-goal navigation system based on our mapping approach, and we validate its efficacy through object-goal navigation, offline object retrieval, and multi-object-goal navigation in both simulated environments and real robot experiments. The findings demonstrate that our method not only exhibits swifter performance than state-of-the-art mapping methods but also surpasses them in terms of the success rate of object-goal navigation tasks.