# SACReg: Scene-Agnostic Coordinate Regression for Visual Localization

arXiv: https://arxiv.org/abs/2307.11702 · HTML: https://mlsanity.com/paper/2307.11702/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 55 of its 98 references that are in the map.
- First posted on arXiv 21 Jul 2023.

## Builds on (most cited first, 30 of 55)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [The Replica Dataset: A Digital Replica of Indoor Spaces](https://mlsanity.com/paper/1906.05797/) (2019)
- [MegaDepth: Learning Single-View Depth Prediction from Internet Photos](https://mlsanity.com/paper/1804.00607/) (2018)
- [Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI](https://mlsanity.com/paper/2109.08238/) (2021)
- [From Coarse to Fine: Robust Hierarchical Localization at Large Scale](https://mlsanity.com/paper/1812.03506/) (2018)
- [Habitat 2.0: Training Home Assistants to Rearrange their Habitat](https://mlsanity.com/paper/2106.14405/) (2021)
- [ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data](https://mlsanity.com/paper/2111.08897/) (2021)
- [DISK: Learning local features with policy gradient](https://mlsanity.com/paper/2006.13566/) (2020)
- [LIFT: Learned Invariant Feature Transform](https://mlsanity.com/paper/1603.09114/) (2016)
- [DSAC - Differentiable RANSAC for Camera Localization](https://mlsanity.com/paper/1611.05705/) (2016)
- [Geometric Loss Functions for Camera Pose Regression with Deep Learning](https://mlsanity.com/paper/1704.00390/) (2017)
- [Non-Local Spatial Propagation Network for Depth Completion](https://mlsanity.com/paper/2007.10042/) (2020)
- [DPOD: 6D Pose Object Detector and Refiner](https://mlsanity.com/paper/1902.11020/) (2019)
- [Learning with Average Precision: Training Image Retrieval with a Listwise Loss](https://mlsanity.com/paper/1906.07589/) (2019)
- [Visual Camera Re-Localization from RGB and RGB-D Images Using DSAC](https://mlsanity.com/paper/2002.12324/) (2020)
- [CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow](https://mlsanity.com/paper/2211.10408/) (2022)
- [Geometry-Aware Learning of Maps for Camera Localization](https://mlsanity.com/paper/1712.03342/) (2017)
- [CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion](https://mlsanity.com/paper/2210.10716/) (2022)
- [LF-Net: Learning Local Features from Images](https://mlsanity.com/paper/1805.09662/) (2018)
- [Learning Less is More - 6D Camera Localization via 3D Surface Regression](https://mlsanity.com/paper/1711.10228/) (2017)
- [PENet: Towards Precise and Efficient Image Guided Depth Completion](https://mlsanity.com/paper/2103.00783/) (2021)
- [SOSNet: Second Order Similarity Regularization for Local Descriptor Learning](https://mlsanity.com/paper/1904.05019/) (2019)

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

- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [3D Reconstruction with Spatial Memory](https://mlsanity.com/paper/2408.16061/) (2024)
- [Cross-View Completion Models are Zero-shot Correspondence Estimators](https://mlsanity.com/paper/2412.09072/) (2024)
- [Outdoor Monocular SLAM with Global Scale-Consistent 3D Gaussian Pointmaps](https://mlsanity.com/paper/2507.03737/) (2025)
- [AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backend](https://mlsanity.com/paper/2511.20343/) (2025)
- [Dense-SfM: Structure from Motion with Dense Consistent Matching](https://mlsanity.com/paper/2501.14277/) (2025)
- [From Sparse to Dense: Camera Relocalization with Scene-Specific Detector from Feature Gaussian Splatting](https://mlsanity.com/paper/2503.19358/) (2025)
- [ACE-G: Improving Generalization of Scene Coordinate Regression Through Query Pre-Training](https://mlsanity.com/paper/2510.11605/) (2025)
- [SceneFactory: A Workflow-centric and Unified Framework for Incremental Scene Modeling](https://mlsanity.com/paper/2405.07847/) (2024)
- [Scene Coordinate Reconstruction Priors](https://mlsanity.com/paper/2510.12387/) (2025)
- [MV-RoMa: From Pairwise Matching into Multi-View Track Reconstruction](https://mlsanity.com/paper/2603.27542/) (2026)
- [MultiLoc: Look Around As You Localize for Fast And Robust Visual Re-localization](https://mlsanity.com/paper/2603.27170/) (2026)
- [Hierarchical Visual Relocalization with Nearest View Synthesis from Feature Gaussian Splatting](https://mlsanity.com/paper/2603.29185/) (2026)
- [Accuracy potential of visual localization exploiting high-end street-level imagery](https://mlsanity.com/paper/2607.24409/) (2026)

## Abstract (arXiv)

Scene coordinates regression (SCR), i.e., predicting 3D coordinates for every pixel of a given image, has recently shown promising potential. However, existing methods remain limited to small scenes memorized during training, and thus hardly scale to realistic datasets and scenarios. In this paper, we propose a generalized SCR model trained once to be deployed in new test scenes, regardless of their scale, without any finetuning. Instead of encoding the scene coordinates into the network weights, our model takes as input a database image with some sparse 2D pixel to 3D coordinate annotations, extracted from e.g. off-the-shelf Structure-from-Motion or RGB-D data, and a query image for which are predicted a dense 3D coordinate map and its confidence, based on cross-attention. At test time, we rely on existing off-the-shelf image retrieval systems and fuse the predictions from a shortlist of relevant database images w.r.t. the query. Afterwards camera pose is obtained using standard Perspective-n-Point (PnP). Starting from selfsupervised CroCo pretrained weights, we train our model on diverse datasets to ensure generalizabilty across various scenarios, and significantly outperform other scene regression approaches, including scene-specific models, on multiple visual localization benchmarks. Finally, we show that the database representation of images and their 2D-3D annotations can be highly compressed with negligible loss of localization performance.