# i3dLoc: Image-to-range Cross-domain Localization Robust to Inconsistent Environmental Conditions

arXiv: https://arxiv.org/abs/2105.12883 · HTML: https://mlsanity.com/paper/2105.12883/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 17 references that are in the map.
- First posted on arXiv 27 May 2021.

## Builds on (most cited first, 7 of 7)

- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM](https://mlsanity.com/paper/2007.11898/) (2020)
- [Spherical CNNs](https://mlsanity.com/paper/1801.10130/) (2018)
- [PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition](https://mlsanity.com/paper/1804.03492/) (2018)
- [OverlapNet: Loop Closing for LiDAR-based SLAM](https://mlsanity.com/paper/2105.11344/) (2021)
- [2D3D-MatchNet: Learning to Match Keypoints Across 2D Image and 3D Point Cloud](https://mlsanity.com/paper/1904.09742/) (2019)
- [Don't Look Back: Robustifying Place Categorization for Viewpoint- and Condition-Invariant Place Recognition](https://mlsanity.com/paper/1801.05078/) (2018)

## Built on by (most cited first, 14 of 14)

- [LIP-Loc: LiDAR Image Pretraining for Cross-Modal Localization](https://mlsanity.com/paper/2312.16648/) (2023)
- [General Place Recognition Survey: Towards Real-World Autonomy](https://mlsanity.com/paper/2405.04812/) (2024)
- [UAVD4L: A Large-Scale Dataset for UAV 6-DoF Localization](https://mlsanity.com/paper/2401.05971/) (2024)
- [BioSLAM: A Bio-inspired Lifelong Memory System for General Place Recognition](https://mlsanity.com/paper/2208.14543/) (2022)
- [General Place Recognition Survey: Towards the Real-world Autonomy Age](https://mlsanity.com/paper/2209.04497/) (2022)
- [AutoMerge: A Framework for Map Assembling and Smoothing in City-scale Environments](https://mlsanity.com/paper/2207.06965/) (2022)
- [iSimLoc: Visual Global Localization for Previously Unseen Environments with Simulated Images](https://mlsanity.com/paper/2209.06376/) (2022)
- [Contrastive Learning of Features between Images and LiDAR](https://mlsanity.com/paper/2206.12071/) (2022)
- [Explicit Interaction for Fusion-Based Place Recognition](https://mlsanity.com/paper/2402.17264/) (2024)
- [SOLVR: Submap Oriented LiDAR-Visual Re-Localisation](https://mlsanity.com/paper/2409.10247/) (2024)
- [Range and Bird's Eye View Fused Cross-Modal Visual Place Recognition](https://mlsanity.com/paper/2502.11742/) (2025)
- [Attention-Enhanced Cross-modal Localization Between 360 Images and Point Clouds](https://mlsanity.com/paper/2212.02757/) (2022)
- [Semi-distributed Cross-modal Air-Ground Relative Localization](https://mlsanity.com/paper/2511.06749/) (2025)
- [UniDA3D: A Unified Domain-Adaptive Framework for Multi-View 3D Object Detection](https://mlsanity.com/paper/2603.27995/) (2026)

## Abstract (arXiv)

We present a method for localizing a single camera with respect to a point cloud map in indoor and outdoor scenes. The problem is challenging because correspondences of local invariant features are inconsistent across the domains between image and 3D. The problem is even more challenging as the method must handle various environmental conditions such as illumination, weather, and seasonal changes. Our method can match equirectangular images to the 3D range projections by extracting cross-domain symmetric place descriptors. Our key insight is to retain condition-invariant 3D geometry features from limited data samples while eliminating the condition-related features by a designed Generative Adversarial Network. Based on such features, we further design a spherical convolution network to learn viewpoint-invariant symmetric place descriptors. We evaluate our method on extensive self-collected datasets, which involve textitLong-term (variant appearance conditions), textitLarge-scale (up to 2km structure/unstructured environment), and textitMultistory (four-floor confined space). Our method surpasses other current state-of-the-arts by achieving around 3 times higher place retrievals to inconsistent environments, and above 3 times accuracy on online localization. To highlight our method's generalization capabilities, we also evaluate the recognition across different datasets. With a single trained model, i3dLoc can demonstrate reliable visual localization in random conditions.