# Unit Region Encoding: A Unified and Compact Geometry-aware Representation for Floorplan Applications

arXiv: https://arxiv.org/abs/2501.11097 · HTML: https://mlsanity.com/paper/2501.11097/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 54 references that are in the map.
- First posted on arXiv 19 Jan 2025.

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

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics](https://mlsanity.com/paper/2011.09127/) (2020)
- [ATISS: Autoregressive Transformers for Indoor Scene Synthesis](https://mlsanity.com/paper/2110.03675/) (2021)
- [SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation](https://mlsanity.com/paper/1711.08588/) (2017)
- [DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation](https://mlsanity.com/paper/2007.11301/) (2020)
- [Fast and Flexible Indoor Scene Synthesis via Deep Convolutional Generative Models](https://mlsanity.com/paper/1811.12463/) (2018)
- [House-GAN: Relational Generative Adversarial Networks for Graph-constrained House Layout Generation](https://mlsanity.com/paper/2003.06988/) (2020)
- [Human-centric Indoor Scene Synthesis Using Stochastic Grammar](https://mlsanity.com/paper/1808.08473/) (2018)
- [Deep Generative Modeling for Scene Synthesis via Hybrid Representations](https://mlsanity.com/paper/1808.02084/) (2018)
- [Topological Map Extraction from Overhead Images](https://mlsanity.com/paper/1812.01497/) (2018)
- [Generative Layout Modeling using Constraint Graphs](https://mlsanity.com/paper/2011.13417/) (2020)
- [Machine-learned Regularization and Polygonization of Building Segmentation Masks](https://mlsanity.com/paper/2007.12587/) (2020)
- [Beyond Fixed Grid: Learning Geometric Image Representation with a Deformable Grid](https://mlsanity.com/paper/2008.09269/) (2020)
- [ActFloor-GAN: Activity-Guided Adversarial Networks for Human-Centric Floorplan Design](https://mlsanity.com/paper/2111.03545/) (2021)
- [Graph-Based Generative Representation Learning of Semantically and Behaviorally Augmented Floorplans](https://mlsanity.com/paper/2012.04735/) (2020)

## Built on by (most cited first, 1 of 1)

- [Training-free Spatially Grounded Geometric Shape Encoding (Technical Report)](https://mlsanity.com/paper/2604.07522/) (2026)

## Abstract (arXiv)

We present the Unit Region Encoding of floorplans, which is a unified and compact geometry-aware encoding representation for various applications, ranging from interior space planning, floorplan metric learning to floorplan generation tasks. The floorplans are represented as the latent encodings on a set of boundary-adaptive unit region partition based on the clustering of the proposed geometry-aware density map. The latent encodings are extracted by a trained network (URE-Net) from the input dense density map and other available semantic maps. Compared to the over-segmented rasterized images and the room-level graph structures, our representation can be flexibly adapted to different applications with the sliced unit regions while achieving higher accuracy performance and better visual quality. We conduct a variety of experiments and compare to the state-of-the-art methods on the aforementioned applications to validate the superiority of our representation, as well as extensive ablation studies to demonstrate the effect of our slicing choices.