Abstract | Keywords | Export | Availability | Bookmark

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Augmented reality is a key technology that will facilitate a major paradigm shift in the way users interact with data and has only just recently been recognized as a viable solution for solving many critical needs. In practical terms, this innovation can be used to visualize data from hundreds of sensors simultaneously, overlaying relevant and actionable information over your environment through a headset. Semantic 3D reconstruction unlocks the promise of AR technology, possessing a far greater availability of semantic information. Although, there are several methods currently available as post-processing approaches to extract semantic information from the reconstructed 3D models, the results obtained results have been uncertain and evenly incorrect. Thus, it is necessary to explore or develop a novel 3D reconstruction approach to automatically recover 3D geometry model and obtained semantic information simultaneously. The rapid advent of deep learning brought new opportunities to the field of semantic 3D reconstruction from photo collections. Deep learning-based methods are not only able to extract semantic information but can also enhance fundamental techniques in semantic 3D reconstruction, techniques which include feature matching or tracking, stereo matching, camera pose estimation, and use of multi-view stereo methods. Moreover, deep learning techniques can be used to extract priors from photo collections, and this obtained information can in turn improve the quality of 3D reconstruction.

Technology: general issues --- History of engineering & technology --- feature tracking --- superpixel --- structure from motion --- three-dimensional reconstruction --- local feature --- multi-view stereo --- construction hazard --- safety education --- photoreality --- virtual reality --- anatomization --- audio classification --- olfactory display --- deep learning --- transfer learning --- inception model --- augmented reality --- higher education --- scientific production --- web of science --- bibliometric analysis --- scientific mapping --- applications in subject areas --- interactive learning environments --- 3P model --- primary education --- educational technology --- mobile lip reading system --- lightweight neural network --- face correction --- virtual reality (VR) --- computer vision --- projection mapping --- 3D face model --- super-resolution --- radial curve --- Dynamic Time Warping --- semantic 3D reconstruction --- eye-in-hand vision system --- robotic manipulator --- probabilistic fusion --- graph-based refinement --- 3D modelling --- 3D representation --- game engine --- laser scanning --- panoramic photography --- super-resolution reconstruction --- generative adversarial networks --- dense convolutional networks --- texture loss --- WGAN-GP --- orientation --- positioning --- viewpoint --- image matching --- algorithm --- transformation --- ADHD --- EDAH --- assessment --- continuous performance test --- Photometric Stereo (PS) --- 3D reconstruction --- fully convolutional network (FCN) --- semi-immersive virtual reality --- children --- cooperative games --- empowerment --- perception --- motor planning --- problem-solving --- area of interest --- wayfinding --- spatial information --- one-shot learning --- gesture recognition --- GREN --- skeleton-based --- 3D composition --- pre-visualization --- stereo vision --- 360° video --- n/a