Neural Scene Decoration from a Single Photograph

TL;DR

This paper introduces neural scene decoration, a novel method for synthesizing furnished indoor scene images from an empty photograph and user-defined layout, simplifying interior design visualization.

Contribution

It proposes a new scene generation architecture that transforms empty scenes and object layouts into realistic furnished images, advancing automated interior scene synthesis.

Findings

Outperforms baseline image translation methods qualitatively and quantitatively

Generates plausible and aesthetically pleasing interior scenes

Validated through extensive experiments

Abstract

Furnishing and rendering indoor scenes has been a long-standing task for interior design, where artists create a conceptual design for the space, build a 3D model of the space, decorate, and then perform rendering. Although the task is important, it is tedious and requires tremendous effort. In this paper, we introduce a new problem of domain-specific indoor scene image synthesis, namely neural scene decoration. Given a photograph of an empty indoor space and a list of decorations with layout determined by user, we aim to synthesize a new image of the same space with desired furnishing and decorations. Neural scene decoration can be applied to create conceptual interior designs in a simple yet effective manner. Our attempt to this research problem is a novel scene generation architecture that transforms an empty scene and an object layout into a realistic furnished scene photograph. We demonstrate the performance of our proposed method by comparing it with conditional image synthesis baselines built upon prevailing image translation approaches both qualitatively and quantitatively. We conduct extensive experiments to further validate the plausibility and aesthetics of our generated scenes. Our implementation is available at \url{https://github.com/hkust-vgd/neural_scene_decoration}.