mlsanityData to 14 Oct 2026

DistillPose: Lightweight Camera Localization Using Auxiliary Learning

arXiv 2108.03819 ↗First posted 9 Aug 2021cs.CVcited by 10

Not on the map. Why?

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.

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

11 of 25 references.

References · 11

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Going Deeper with Convolutionscited by 4,241
  3. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  4. 2016LIFT: Learned Invariant Feature Transformcited by 306
  5. 2016DSAC - Differentiable RANSAC for Camera Localizationcited by 266
  6. 2017Geometric Loss Functions for Camera Pose Regression with Deep Learningcited by 224
  7. 2016Image-based localization using LSTMs for structured feature correlationcited by 136
  8. 2015Modelling Uncertainty in Deep Learning for Camera Relocalizationcited by 134
  9. 2017Camera Relocalization by Computing Pairwise Relative Poses Using Convolutional Neural Networkcited by 79
  10. 2019Introduction to Camera Pose Estimation with Deep Learningcited by 25
  11. 2018Improved Visual Relocalization by Discovering Anchor Pointscited by 16

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 1; 2024: 3; 2025: 2; 2026: 2.

10 papers.

  1. 2022Map-free Visual Relocalization: Metric Pose Relative to a Single Imagecited by 114
  2. 2024Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localizationcited by 82
  3. 2022Leveraging Image Matching Toward End-to-End Relative Camera Pose Regressioncited by 6
  4. 2024Obfuscation Based Privacy Preserving Representations are Recoverable Using Neighborhood Informationcited by 6
  5. 2024SRPose: Two-view Relative Pose Estimation with Sparse Keypointscited by 5
  6. 2026Video Understanding: From Geometry and Semantics to Unified Modelscited by 5
  7. 2023OFVL-MS: Once for Visual Localization across Multiple Indoor Scenescited by 3
  8. 2025GRLoc: Geometric Representation Regression for Visual Localizationcited by 1
  9. 2025Multiview Image-Based Localizationcited by 0
  10. 2026IUP-Pose: Decoupled Iterative Uncertainty Propagation for Real-time Relative Pose Regression via Implicit Dense Alignment v1cited by 0