Joint Layout Estimation and Global Multi-View Registration for Indoor Reconstruction: Supplementary Material

Registration of Partial 3D Point Clouds Acquired from a Multi-view Camera for Indoor Scene Reconstruction

In this paper, a novel projection-based method is presented to register partial 3D point clouds, acquired from a multi-view camera, for 3D reconstruction of an indoor scene. In general, conventional registration methods for partial 3D point clouds require a high computational complexity and much time for registration. Moreover, these methods are not robust for 3D point cloud which has a low pre...

Supplementary Material Multi-view Non-rigid Refinement and Normal Selection for High Quality 3D Reconstruction

Indoor Augmented Reality using 3D Scene Reconstruction

This project report describes the design and implementation of a mobile application that works in conjunction with a structure and layout estimation module to generate an interactive model of an indoor scene from a series of images captured using the mobile device. In particular, methods for automatically frame selection, motion estimation, and image mosaicing are investigated.

Knowing Where I Am: Exploiting Multi-Task Learning for Multi-view Indoor Image-based Localization

Indoor localization has attracted a large amount of applications in mobile and robotics area, especially in vast and sophisticated environments. Most indoor localization methods are based on cellular base stations and WiFi signals. Such methods require users to carry additional equipment. Localization accuracy is largely based on the beacon distribution. Image-based localization is mainly appli...

Harvesting Multiple Views for Marker-less 3D Human Pose Annotations Supplementary Material

In this supplementary, we provide material that could not be included in the main manuscript due to space constraints. Section 1 provides additional quantitative evaluation of our approach for multi-view pose estimation, and comparison with the state-of-the-art for HumanEva-I [4]. Section 2 provides full results of the multi-view optimization on Human3.6M after refining the generic 2D pose Conv...