mlsanityData to 7 Oct 2026

PoseINN: Realtime Visual-based Pose Regression and Localization with Invertible Neural Networks

arXiv 2404.13288 ↗First posted 20 Apr 2024cs.RO cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Estimating ego-pose from cameras is an important problem in robotics with applications ranging from mobile robotics to augmented reality. While SOTA models are becoming increasingly accurate, they can still be unwieldy due to high computational costs. In this paper, we propose to solve the problem by using invertible neural networks (INN) to find the mapping between the latent space of images and poses for a given scene. Our model achieves similar performance to the SOTA while being faster to train and only requiring offline rendering of low-resolution synthetic data. By using normalizing flows, the proposed method also provides uncertainty estimation for the output. We also demonstrated the efficiency of this method by deploying the model on a mobile robot.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 24 of its 36 references that are in the map. First posted on arXiv 20 Apr 2024.

Builds on

24 of 36 references.

References · 24

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  3. 2016Density estimation using Real NVPcited by 2,029
  4. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  5. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,186
  6. 2023Nerfstudio: A Modular Framework for Neural Radiance Field Developmentcited by 596
  7. 2018An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solutioncited by 302
  8. 2018Analyzing Inverse Problems with Invertible Neural Networkscited by 239
  9. 2019Learning Likelihoods with Conditional Normalizing Flowscited by 170
  10. 2019Guided Image Generation with Conditional Invertible Neural Networkscited by 147
  11. 2015Modelling Uncertainty in Deep Learning for Camera Relocalizationcited by 133
  12. 2021LENS: Localization enhanced by NeRF synthesiscited by 116
12 more
  1. 2021Learning Multi-Scene Absolute Pose Regression with Transformerscited by 108
  2. 2019AtLoc: Attention Guided Camera Localizationcited by 92
  3. 2021Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flowscited by 84
  4. 2022DFNet: Enhance Absolute Pose Regression with Direct Feature Matchingcited by 82
  5. 2017Image-based Localization using Hourglass Networkscited by 63
  6. 2021Direct-PoseNet: Absolute Pose Regression with Photometric Consistencycited by 61
  7. 2021CoordiNet: uncertainty-aware pose regressor for reliable vehicle localizationcited by 34
  8. 2022Camera Pose Auto-Encoders for Improving Pose Regressioncited by 28
  9. 2023A Probabilistic Framework for Visual Localization in Ambiguous Scenescited by 12
  10. 2017CDDT: Fast Approximate 2D Ray Casting for Accelerated Localizationcited by 9
  11. 2019Uncertainty-aware performance assessment of optical imaging modalities with invertible neural networkscited by 5
  12. 2022Local_INN: Implicit Map Representation and Localization with Invertible Neural Networkscited by 2

Built on by

Not cited yet.