# Scene Representation using 360deg Saliency Graph and its Application in Vision-based Indoor Navigation

arXiv: https://arxiv.org/abs/2603.20353 · HTML: https://mlsanity.com/paper/2603.20353/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 40 of its 62 references that are in the map.
- First posted on arXiv 20 Mar 2026.

## Builds on (most cited first, 30 of 40)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environments](https://mlsanity.com/paper/1904.10151/) (2019)
- [Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation](https://mlsanity.com/paper/1811.10092/) (2018)
- [Neural Topological SLAM for Visual Navigation](https://mlsanity.com/paper/2005.12256/) (2020)
- [GANalyze: Toward Visual Definitions of Cognitive Image Properties](https://mlsanity.com/paper/1906.10112/) (2019)
- [Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigation](https://mlsanity.com/paper/2202.11742/) (2022)
- [Simple but Effective: CLIP Embeddings for Embodied AI](https://mlsanity.com/paper/2111.09888/) (2021)
- [COTR: Correspondence Transformer for Matching Across Images](https://mlsanity.com/paper/2103.14167/) (2021)
- [ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer](https://mlsanity.com/paper/2208.14201/) (2022)
- [ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environments](https://mlsanity.com/paper/2304.03047/) (2023)
- [ASLFeat: Learning Local Features of Accurate Shape and Localization](https://mlsanity.com/paper/2003.10071/) (2020)
- [Airbert: In-domain Pretraining for Vision-and-Language Navigation](https://mlsanity.com/paper/2108.09105/) (2021)
- [Waypoint Models for Instruction-guided Navigation in Continuous Environments](https://mlsanity.com/paper/2110.02207/) (2021)
- [QuadTree Attention for Vision Transformers](https://mlsanity.com/paper/2201.02767/) (2022)
- [Pathdreamer: A World Model for Indoor Navigation](https://mlsanity.com/paper/2105.08756/) (2021)
- [EnvEdit: Environment Editing for Vision-and-Language Navigation](https://mlsanity.com/paper/2203.15685/) (2022)
- [ALIKE: Accurate and Lightweight Keypoint Detection and Descriptor Extraction](https://mlsanity.com/paper/2112.02906/) (2021)
- [HOP: History-and-Order Aware Pre-training for Vision-and-Language Navigation](https://mlsanity.com/paper/2203.11591/) (2022)
- [Learning Object Relation Graph and Tentative Policy for Visual Navigation](https://mlsanity.com/paper/2007.11018/) (2020)
- [Volumetric Environment Representation for Vision-Language Navigation](https://mlsanity.com/paper/2403.14158/) (2024)
- [Topological Semantic Graph Memory for Image-Goal Navigation](https://mlsanity.com/paper/2209.08274/) (2022)
- [Curious Representation Learning for Embodied Intelligence](https://mlsanity.com/paper/2105.01060/) (2021)
- [Learning Navigational Visual Representations with Semantic Map Supervision](https://mlsanity.com/paper/2307.12335/) (2023)
- [A Behavioral Approach to Visual Navigation with Graph Localization Networks](https://mlsanity.com/paper/1903.00445/) (2019)

## Abstract (arXiv)

A Scene, represented visually using different formats such as RGB-D, LiDAR scan, keypoints, rectangular, spherical, multi-views, etc., contains information implicitly embedded relevant to applications such as scene indexing, vision-based navigation. Thus, these representations may not be efficient for such applications. This paper proposes a novel 360deg saliency graph representation of the scenes. This rich representation explicitly encodes the relevant visual, contextual, semantic, and geometric information of the scene as nodes, edges, edge weights, and angular position in the 360deg graph. Also, this representation is robust against scene view change and addresses challenges of indoor environments such as varied illumination, occlusions, and shadows as in the case of existing traditional methods. We have utilized this rich and efficient representation for vision-based navigation and compared it with existing navigation methods using 360deg scenes. However, these existing methods suffer from limitations of poor scene representation, lacking scene-specific information. This work utilizes the proposed representation first to localize the query scene in the given topological map, and then facilitate 2D navigation by estimating the next required movement directions towards the target destination in the topological map by using the embedded geometric information in the 360deg saliency graph. Experimental results demonstrate the efficacy of the proposed 360deg saliency graph representation in enhancing both scene localization and vision-based indoor navigation.