Floorplan Restoration by Structure Hallucinating Transformer Cascades
This addresses a specific challenge in architectural reconstruction for applications like virtual tours or building analysis, representing an incremental advance in floorplan restoration.
The paper tackles the problem of reconstructing complete floorplans from partial reconstructions by hallucinating invisible rooms and doors, achieving state-of-the-art performance on a new benchmark of 701 houses.
This paper presents an extreme floorplan reconstruction task, a new benchmark for the task, and a neural architecture as a solution. Given a partial floorplan reconstruction inferred or curated from panorama images, the task is to reconstruct a complete floorplan including invisible architectural structures. The proposed neural network 1) encodes an input partial floorplan into a set of latent vectors by convolutional neural networks and a Transformer; and 2) reconstructs an entire floorplan while hallucinating invisible rooms and doors by cascading Transformer decoders. Qualitative and quantitative evaluations demonstrate effectiveness of our approach over the benchmark of 701 houses, outperforming the state-of-the-art reconstruction techniques. We will share our code, models, and data.