Transferable End-to-end Room Layout Estimation via Implicit Encoding

Abstract

We study the problem of estimating room layouts from a single panorama image. Most former works have two stages: feature extraction and parametric model fitting.Here we propose an end-to-end method that directly predicts parametric layouts from an input panorama image. It exploits an implicit encoding procedure that embeds parametric layouts into a latent space. Then learning a mapping from images to this latent space makes end-to-end room layout estimation possible. However end-to-end methods have several notorious drawbacks despite many intriguing properties. A widely raised criticism is that they are troubled with dataset bias and do not transfer to unfamiliar domains. Our study echos this common belief. To this end, we propose to use semantic boundary prediction maps as an intermediate domain. It brings significant performance boost on four benchmarks (Structured3D, PanoContext, S3DIS, and Mat-terport3D), notably in the zero-shot transfer setting. Code, data, and models will be released.

From Semi-supervised to Omni-supervised Room Layout Estimation Using Point Clouds

“…Over the past decade, room layout estimation has drawn a lot of attention from the robotics community [1]- [6] since it marks a crucial step towards understanding indoor scenes and might help robot agents make better decisions in challenging environments [7]- [10]. However, the majority of earlier efforts exploit perspective or panoramic RGB images as input [11]- [28], whereas the promising paradigm of layout estimation using point clouds (PCs) [29] still suffers from the lack of annotated data.…”