activity
20182022
collaborators

6 papers

cs.CV2022

Self-Supervised Ego-Motion Estimation Based on Multi-Layer Fusion of RGB and Inferred Depth

Zijie Jiang, Hajime Taira, Naoyuki Miyashita +1

In existing self-supervised depth and ego-motion estimation methods, ego-motion estimation is usually limited to only leveraging RGB information. Recently, several methods have bee…

cs.CV2021

Video-Based Camera Localization Using Anchor View Detection and Recursive 3D Reconstruction

Hajime Taira, Koki Onbe, Naoyuki Miyashita +1

In this paper we introduce a new camera localization strategy designed for image sequences captured in challenging industrial situations such as industrial parts inspection. To dea…

cs.CV2021

VIO-Aided Structure from Motion Under Challenging Environments

Zijie Jiang, Hajime Taira, Naoyuki Miyashita +1

In this paper, we present a robust and efficient Structure from Motion pipeline for accurate 3D reconstruction under challenging environments by leveraging the camera pose informat…

cs.CV2020

3D Pipe Network Reconstruction Based on Structure from Motion with Incremental Conic Shape Detection and Cylindrical Constraint

Sho kagami, Hajime Taira, Naoyuki Miyashita +2

Pipe inspection is a critical task for many industries and infrastructure of a city. The 3D information of a pipe can be used for revealing the deformation of the pipe surface and…

cs.CV2019

Is This The Right Place? Geometric-Semantic Pose Verification for Indoor Visual Localization

Hajime Taira, Ignacio Rocco, Jiri Sedlar +5

Visual localization in large and complex indoor scenes, dominated by weakly textured rooms and repeating geometric patterns, is a challenging problem with high practical relevance…

cs.CV2018

InLoc: Indoor Visual Localization with Dense Matching and View Synthesis

Hajime Taira, Masatoshi Okutomi, Torsten Sattler +5

We seek to predict the 6 degree-of-freedom (6DoF) pose of a query photograph with respect to a large indoor 3D map. The contributions of this work are three-fold. First, we develop…