# Floorplan Restoration by Structure Hallucinating Transformer Cascades

arXiv: https://arxiv.org/abs/2206.00645 · HTML: https://mlsanity.com/paper/2206.00645/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 35 references that are in the map.
- First posted on arXiv 1 Jun 2022.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [RePaint: Inpainting using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.09865/) (2022)
- [Free-Form Image Inpainting with Gated Convolution](https://mlsanity.com/paper/1806.03589/) (2018)
- [DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction](https://mlsanity.com/paper/1905.10711/) (2019)
- [MAT: Mask-Aware Transformer for Large Hole Image Inpainting](https://mlsanity.com/paper/2203.15270/) (2022)
- [HorizonNet: Learning Room Layout with 1D Representation and Pano Stretch Data Augmentation](https://mlsanity.com/paper/1901.03861/) (2019)
- [Semantic Amodal Segmentation](https://mlsanity.com/paper/1509.01329/) (2015)
- [Self-Supervised Scene De-occlusion](https://mlsanity.com/paper/2004.02788/) (2020)
- [Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encoding](https://mlsanity.com/paper/2203.00867/) (2022)
- [Diverse Image Inpainting with Bidirectional and Autoregressive Transformers](https://mlsanity.com/paper/2104.12335/) (2021)
- [DuLa-Net: A Dual-Projection Network for Estimating Room Layouts from a Single RGB Panorama](https://mlsanity.com/paper/1811.11977/) (2018)
- [Neural Illumination: Lighting Prediction for Indoor Environments](https://mlsanity.com/paper/1906.07370/) (2019)
- [Floor-SP: Inverse CAD for Floorplans by Sequential Room-wise Shortest Path](https://mlsanity.com/paper/1908.06702/) (2019)
- [FloorNet: A Unified Framework for Floorplan Reconstruction from 3D Scans](https://mlsanity.com/paper/1804.00090/) (2018)
- [MonteFloor: Extending MCTS for Reconstructing Accurate Large-Scale Floor Plans](https://mlsanity.com/paper/2103.11161/) (2021)
- [Extreme Relative Pose Estimation for RGB-D Scans via Scene Completion](https://mlsanity.com/paper/1901.00063/) (2018)
- [Floorplan-Jigsaw: Jointly Estimating Scene Layout and Aligning Partial Scans](https://mlsanity.com/paper/1812.06677/) (2018)

## Built on by (most cited first, 4 of 4)

- [PuzzleFusion: Unleashing the Power of Diffusion Models for Spatial Puzzle Solving](https://mlsanity.com/paper/2211.13785/) (2022)
- [Generative AI Models for Different Steps in Architectural Design: A Literature Review](https://mlsanity.com/paper/2404.01335/) (2024)
- [Computer-Aided Layout Generation for Building Design: A Review](https://mlsanity.com/paper/2504.09694/) (2025)
- [Unified Vector Floorplan Generation via Markup Representation](https://mlsanity.com/paper/2604.04859/) (2026)

## Abstract (arXiv)

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.