English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Estimating the layout of a room from a single-shot panoramic image isimportant in virtual/augmented reality and furniture layout simulation. Thisinvolves identifying three-dimensional (3D) geometry, such as the location ofcorners and boundaries, and performing 3D reconstruction. However, occlusion isa common issue that can negatively impact room layout estimation, and this hasnot been thoroughly studied to date. It is possible to obtain 3D shapeinformation of rooms as drawings of buildings and coordinates of corners fromimage datasets, thus we propose providing both 2D panoramic and 3D informationto a model to effectively deal with occlusion. However, simply feeding 3Dinformation to a model is not sufficient to utilize the shape information foran occluded area. Therefore, we improve the model by introducing 3DIntersection over Union (IoU) loss to effectively use 3D information. In somecases, drawings are not available or the construction deviates from a drawing.Considering such practical cases, we propose a method for distilling knowledgefrom a model trained with both images and 3D information to a model that takesonly images as input. The proposed model, which is called Shape-Net, achievesstate-of-the-art (SOTA) performance on benchmark datasets. We also confirmedits effectiveness in dealing with occlusion through significantly improvedaccuracy on images with occlusion compared with existing models.

Shape-Net: Room Layout Estimation from Panoramic Images Robust to Occlusion using Knowledge Distillation with 3D Shapes as Additional Inputs