6 papers
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…
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…
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…
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…
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…
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…