# DPC-Net: Deep Pose Correction for Visual Localization

Source: [DPC-Net: Deep Pose Correction for Visual Localization](<https://www.sota2.com/research/paper/68fa6cf81e209131cea36f3c>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T00:22:36.594Z

Authors: Valentin Peretroukhin, Jonathan Kelly

Published: 2017-09-10T16:35:55.000Z

## Abstract

We present a novel method to fuse the power of deep networks with the computational efficiency of geometric and probabilistic localization algorithms. In contrast to other methods that completely replace a classical visual estimator with a deep network, we propose an approach that uses a convolutional neural network to learn difficult-to-model corrections to the estimator from ground-truth training data. To this end, we derive a novel loss function for learning SE(3) corrections based on a matrix Lie groups approach, with a natural formulation for balancing translation and rotation errors. We use this loss to train a Deep Pose Correction network (DPC-Net) that predicts corrections for a particular estimator, sensor and environment. Using the KITTI odometry dataset, we demonstrate significant improvements to the accuracy of a computationally-efficient sparse stereo visual odometry pipeline, that render it as accurate as a modern computationally-intensive dense estimator. Further, we show how DPC-Net can be used to mitigate the effect of poorly calibrated lens distortion parameters.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Pose Correction on EuRoC](<https://www.sota2.com/research/sota/pose-correction-on-euroc.md>): Pose Correction; EuRoC; RMSE: 0.027.

- [Pose Correction on UnCal-Flight Yaw Forward](<https://www.sota2.com/research/sota/pose-correction-on-uncal-flight-yaw-forward.md>): Pose Correction; UnCal-Flight Yaw Forward; RMSE (m): 0.059.

- [Pose Correction on UnCal-Flight (Yaw Constant)](<https://www.sota2.com/research/sota/pose-correction-on-uncal-flight-yaw-constant.md>): Pose Correction; UnCal-Flight (Yaw Constant); RMSE (m): 0.045.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1709.03128>)

[PDF](<https://arxiv.org/pdf/1709.03128.pdf>)