Layout Aware Inpainting for Automated Furniture Removal in Indoor Scenes

TL;DR

This paper presents a layout-aware inpainting method for automatically removing furniture from indoor scene images, ensuring geometric consistency and enabling virtual redecoration.

Contribution

It introduces a novel approach utilizing perceptual information like instance segmentation and room layout for geometrically consistent inpainting of large regions.

Findings

Effective furniture removal with geometric consistency

Automatic rectification improves inpainting quality

Application demonstrated with virtual redecoration

Abstract

We address the problem of detecting and erasing furniture from a wide angle photograph of a room. Inpainting large regions of an indoor scene often results in geometric inconsistencies of background elements within the inpaint mask. To address this problem, we utilize perceptual information (e.g. instance segmentation, and room layout) to produce a geometrically consistent empty version of a room. We share important details to make this system viable, such as per-plane inpainting, automatic rectification, and texture refinement. We provide detailed ablation along with qualitative examples, justifying our design choices. We show an application of our system by removing real furniture from a room and redecorating it with virtual furniture.