ViPR: Visual-Odometry-aided Pose Regression for 6DoF Camera Localization

TL;DR

ViPR introduces a modular architecture that combines absolute and relative pose estimates using recurrent layers, significantly improving long-term 6DoF visual odometry performance in challenging scenarios.

Contribution

The paper presents a novel modular framework that integrates pose regression and optical flow for enhanced long-term 6DoF visual odometry.

Findings

Outperforms state-of-the-art in long-term navigation tasks

Effective integration of absolute and relative pose estimates

Demonstrated on multiple datasets including Industry dataset

Abstract

Visual Odometry (VO) accumulates a positional drift in long-term robot navigation tasks. Although Convolutional Neural Networks (CNNs) improve VO in various aspects, VO still suffers from moving obstacles, discontinuous observation of features, and poor textures or visual information. While recent approaches estimate a 6DoF pose either directly from (a series of) images or by merging depth maps with optical flow (OF), research that combines absolute pose regression with OF is limited. We propose ViPR, a novel modular architecture for long-term 6DoF VO that leverages temporal information and synergies between absolute pose estimates (from PoseNet-like modules) and relative pose estimates (from FlowNet-based modules) by combining both through recurrent layers. Experiments on known datasets and on our own Industry dataset show that our modular design outperforms state of the art in long-term navigation tasks.