# DistillPose: Lightweight Camera Localization Using Auxiliary Learning

arXiv: https://arxiv.org/abs/2108.03819 · HTML: https://mlsanity.com/paper/2108.03819/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 25 references that are in the map.
- First posted on arXiv 9 Aug 2021.

## Builds on (most cited first, 11 of 11)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [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)
- [Image-based localization using LSTMs for structured feature correlation](https://mlsanity.com/paper/1611.07890/) (2016)
- [Modelling Uncertainty in Deep Learning for Camera Relocalization](https://mlsanity.com/paper/1509.05909/) (2015)
- [Camera Relocalization by Computing Pairwise Relative Poses Using Convolutional Neural Network](https://mlsanity.com/paper/1707.09733/) (2017)
- [Introduction to Camera Pose Estimation with Deep Learning](https://mlsanity.com/paper/1907.05272/) (2019)
- [Improved Visual Relocalization by Discovering Anchor Points](https://mlsanity.com/paper/1811.04370/) (2018)

## Built on by (most cited first, 10 of 10)

- [Map-free Visual Relocalization: Metric Pose Relative to a Single Image](https://mlsanity.com/paper/2210.05494/) (2022)
- [Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization](https://mlsanity.com/paper/2412.08376/) (2024)
- [Leveraging Image Matching Toward End-to-End Relative Camera Pose Regression](https://mlsanity.com/paper/2211.14950/) (2022)
- [Obfuscation Based Privacy Preserving Representations are Recoverable Using Neighborhood Information](https://mlsanity.com/paper/2409.11536/) (2024)
- [SRPose: Two-view Relative Pose Estimation with Sparse Keypoints](https://mlsanity.com/paper/2407.08199/) (2024)
- [Video Understanding: From Geometry and Semantics to Unified Models](https://mlsanity.com/paper/2603.17840/) (2026)
- [OFVL-MS: Once for Visual Localization across Multiple Indoor Scenes](https://mlsanity.com/paper/2308.11928/) (2023)
- [GRLoc: Geometric Representation Regression for Visual Localization](https://mlsanity.com/paper/2511.13864/) (2025)
- [Multiview Image-Based Localization](https://mlsanity.com/paper/2503.23577/) (2025)
- [IUP-Pose: Decoupled Iterative Uncertainty Propagation for Real-time Relative Pose Regression via Implicit Dense Alignment v1](https://mlsanity.com/paper/2603.19625/) (2026)

## Abstract (arXiv)

We propose a lightweight retrieval-based pipeline to predict 6DOF camera poses from RGB images. Our pipeline uses a convolutional neural network (CNN) to encode a query image as a feature vector. A nearest neighbor lookup finds the pose-wise nearest database image. A siamese convolutional neural network regresses the relative pose from the nearest neighboring database image to the query image. The relative pose is then applied to the nearest neighboring absolute pose to obtain the query image's final absolute pose prediction. Our model is a distilled version of NN-Net that reduces its parameters by 98.87%, information retrieval feature vector size by 87.5%, and inference time by 89.18% without a significant decrease in localization accuracy.