# Domain Adaptation of Networks for Camera Pose Estimation: Learning Camera Pose Estimation Without Pose Labels

arXiv: https://arxiv.org/abs/2111.14741 · HTML: https://mlsanity.com/paper/2111.14741/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 45 references that are in the map.
- First posted on arXiv 29 Nov 2021.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras](https://mlsanity.com/paper/1610.06475/) (2016)
- [Solving Rubik's Cube with a Robot Hand](https://mlsanity.com/paper/1910.07113/) (2019)
- [Contrastive Learning for Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2007.15651/) (2020)
- [From Coarse to Fine: Robust Hierarchical Localization at Large Scale](https://mlsanity.com/paper/1812.03506/) (2018)
- [Bidirectional Learning for Domain Adaptation of Semantic Segmentation](https://mlsanity.com/paper/1904.10620/) (2019)
- [Back to the Feature: Learning Robust Camera Localization from Pixels to Pose](https://mlsanity.com/paper/2103.09213/) (2021)
- [Understanding the Limitations of CNN-based Absolute Camera Pose Regression](https://mlsanity.com/paper/1903.07504/) (2019)
- [Visual Camera Re-Localization from RGB and RGB-D Images Using DSAC](https://mlsanity.com/paper/2002.12324/) (2020)
- [Image-based localization using LSTMs for structured feature correlation](https://mlsanity.com/paper/1611.07890/) (2016)
- [se(3)-TrackNet: Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic Domains](https://mlsanity.com/paper/2007.13866/) (2020)
- [Expert Sample Consensus Applied to Camera Re-Localization](https://mlsanity.com/paper/1908.02484/) (2019)
- [Robust Image Retrieval-based Visual Localization using Kapture](https://mlsanity.com/paper/2007.13867/) (2020)
- [VLocNet++: Deep Multitask Learning for Semantic Visual Localization and Odometry](https://mlsanity.com/paper/1804.08366/) (2018)
- [Large-scale, real-time visual-inertial localization revisited](https://mlsanity.com/paper/1907.00338/) (2019)
- [SegMap: Segment-based mapping and localization using data-driven descriptors](https://mlsanity.com/paper/1909.12837/) (2019)
- [On-the-Fly Adaptation of Regression Forests for Online Camera Relocalisation](https://mlsanity.com/paper/1702.02779/) (2017)
- [Real-Time RGB-D Camera Pose Estimation in Novel Scenes using a Relocalisation Cascade](https://mlsanity.com/paper/1810.12163/) (2018)
- [UcoSLAM: Simultaneous Localization and Mapping by Fusion of KeyPoints and Squared Planar Markers](https://mlsanity.com/paper/1902.03729/) (2019)
- [Robust RGB-based 6-DoF Pose Estimation without Real Pose Annotations](https://mlsanity.com/paper/2008.08391/) (2020)
- [REST: Real-to-Synthetic Transform for Illumination Invariant Camera Localization](https://mlsanity.com/paper/1803.09448/) (2018)
- [Augmenting Visual SLAM with Wi-Fi Sensing For Indoor Applications](https://mlsanity.com/paper/1903.06687/) (2019)

## Abstract (arXiv)

One of the key criticisms of deep learning is that large amounts of expensive and difficult-to-acquire training data are required in order to train models with high performance and good generalization capabilities. Focusing on the task of monocular camera pose estimation via scene coordinate regression (SCR), we describe a novel method, Domain Adaptation of Networks for Camera pose Estimation (DANCE), which enables the training of models without access to any labels on the target task. DANCE requires unlabeled images (without known poses, ordering, or scene coordinate labels) and a 3D representation of the space (e.g., a scanned point cloud), both of which can be captured with minimal effort using off-the-shelf commodity hardware. DANCE renders labeled synthetic images from the 3D model, and bridges the inevitable domain gap between synthetic and real images by applying unsupervised image-level domain adaptation techniques (unpaired image-to-image translation). When tested on real images, the SCR model trained with DANCE achieved comparable performance to its fully supervised counterpart (in both cases using PnP-RANSAC for final pose estimation) at a fraction of the cost. Our code and dataset are available at https://github.com/JackLangerman/dance