IM2CAD

TL;DR

This paper introduces an automatic system that reconstructs indoor scenes from a single photo by optimizing furniture placement and scale using deep learning, achieving high-quality results and improving scene understanding benchmarks.

Contribution

The novel approach jointly optimizes scene layout and object placement using deep neural networks, enabling accurate scene reconstruction from a single image.

Findings

High-quality scene reconstruction from a single photo

Significant improvement on scene understanding benchmarks

Effective joint optimization of object placement and scale

Abstract

Given a single photo of a room and a large database of furniture CAD models, our goal is to reconstruct a scene that is as similar as possible to the scene depicted in the photograph, and composed of objects drawn from the database. We present a completely automatic system to address this IM2CAD problem that produces high quality results on challenging imagery from interior home design and remodeling websites. Our approach iteratively optimizes the placement and scale of objects in the room to best match scene renderings to the input photo, using image comparison metrics trained via deep convolutional neural nets. By operating jointly on the full scene at once, we account for inter-object occlusions. We also show the applicability of our method in standard scene understanding benchmarks where we obtain significant improvement.