IM2CAD
This addresses the problem of automated 3D scene reconstruction for interior design and remodeling applications, representing a novel method for a known bottleneck.
The paper tackles the problem of reconstructing a 3D scene from a single photo using a furniture CAD database, achieving high-quality results on challenging interior design imagery. It demonstrates significant improvement in standard scene understanding benchmarks.
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.