Automatic 3D reconstruction of indoor spaces from 2D floor plans necessitates high-precision semantic segmentation of structural elements, particularly walls. However, existing methods often struggle with detecting thin structures and maintaining geometric precision. To address this, we introduce MitUNet, a hybrid neural network designed to bridge the gap between global semantic context and fine-grained structural details. Our architecture combines a Mix-Transformer encoder with a U-Net decoder enhanced with spatial and channel attention blocks. Optimized with the Tversky loss function, this approach achieves a balance between precision and recall, ensuring accurate boundary recovery. Experiments on the CubiCasa5k dataset and the regional dataset demonstrate MitUNet's superiority in generating structurally correct masks with high boundary accuracy, outperforming standard models. This tool provides a robust foundation for automated 3D reconstruction pipelines. To ensure reproducibility and facilitate future research, the source code and the regional dataset are publicly available at https://github.com/aliasstudio/mitunet and https://doi.org/10.5281/zenodo.17871079, respectively.
In this paper, we present a GNN-based Line Segment Parser (GLSP), which uses a junction heatmap to predict line segments' endpoints, and graph neural networks to extract line segments and their categories. Different from previous floor plan recognition methods, which rely on semantic segmentation, our proposed method is able to output vectorized line segment and requires less post-processing steps to be put into practical use. Our experiments show that the methods outperform state-of-the-art line segment detection models on multi-class line segment detection tasks with floor plan images. In th…
This papers focuses on symbol spotting on real-world digital architectural floor plans with a deep learning (DL)-based framework. Traditional on-the-fly symbol spotting methods are unable to address the semantic challenge of graphical notation variability, i.e. low intra-class symbol similarity, an issue that is particularly important in architectural floor plan analysis. The presence of occlusion and clutter, characteristic of real-world plans, along with a varying graphical symbol complexity from almost trivial to highly complex, also pose challenges to existing spotting methods. In this pap…
This paper presents a new approach for the recognition of elements in floor plan layouts. Besides of elements with common shapes, we aim to recognize elements with irregular shapes such as circular rooms and inclined walls. Furthermore, the reduction of noise in the semantic segmentation of the floor plan is on demand. To this end, we propose direction-aware, learnable, additive kernels in the application of both the context module and common convolutional blocks. We apply them for high performance of elements with both common and irregular shapes. Besides, an adversarial network with two disc…
COMPASS: COmpact Multi-channel Prior-map And Scene Signature for Floor-Plan-Based Visual Localization
Automation and Robotics Research Group, Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg (UL)（自动化与机器人研究组，安全、可靠性与信任跨学科中心（SnT），卢森堡大学（UL））
Amrita Vishwa Vidyapeetham（阿姆里塔维什瓦维迪亚皮特姆大学）；RBG.AI, Resilience Business Grids LLP（RBG.AI，韧性商业网格有限责任公司）
Building Information Modelling (BIM) software use scalable vector formats to enable flexible designing of floor plans in the industry. Floor plans in the architectural domain can come from many sources that may or may not be in scalable vector format. The conversion of floor plan images to fully annotated vector images is a process that can now be realized by computer vision. Novel datasets in this field have been used to train Convolutional Neural Network (CNN) architectures for object detection. Image enhancement through Super-Resolution (SR) is also an established CNN based network in compu…
This paper presents a deep learning-based point cloud processing method named FloorPP-Net for the task of Scan-to-BIM (building information model). FloorPP-Net first converts the input point cloud of a building story into point pillars (PP), then predicts the corners and edges to output the floor plan. Altogether, FloorPP-Net establishes an end-to-end supervised learning framework for the Scan-to-Floor-Plan (Scan2FP) task. In the 1st International Scan-to-BIM Challenge held in conjunction with CVPR 2021, FloorPP-Net was ranked the second runner-up in the floor plan reconstruction track. Future…
FloNa: Floor Plan Guided Embodied Visual Navigation
Beijing Institute of Technology（北京理工大学）；Yangtze Delta Region Academy of Beijing Institute of Technology（北京理工大学长三角研究院）；Beijing Racobit Electronic Information Technology Co., Ltd.（北京睿科比特电子信息技术有限公司）
Floor plans are the basis of reasoning in and communicating about indoor environments. In this paper, we show that by modelling floor plans as sequences of line segments seen from a particular point of view, recent advances in autoregressive sequence modelling can be leveraged to model and predict floor plans. The line segments are canonicalized and translated to sequence of tokens and an attention-based neural network is used to fit a one-step distribution over next tokens. We fit the network to sequences derived from a set of large-scale floor plans, and demonstrate the capabilities of the m…
In recent years, floor plan segmentation has gained significant attention due to its wide range of applications in floor plan reconstruction and robotics. In this paper, we propose a novel 2D floor plan segmentation technique based on a down-sampling approach. Our method employs continuous down-sampling on a floor plan to maintain its structural information while reducing its complexity. We demonstrate the effectiveness of our approach by presenting results obtained from both cluttered floor plans generated by a vacuum cleaning robot in unknown environments and a benchmark of floor plans. Our …
Human beings understand natural language description and could able to imagine a corresponding visual for the same. For example, given a description of the interior of a house, we could imagine its structure and arrangements of furniture. Automatic synthesis of real-world images from text descriptions has been explored in the computer vision community. However, there is no such attempt in the area of document images, like floor plans. Floor plan synthesis from sketches, as well as data-driven models, were proposed earlier. Ours is the first attempt to render building floor plan images from tex…
FloorSAM: SAM-Guided Floorplan Reconstruction with Semantic-Geometric Fusion
College of Information Engineering, Zhejiang University of Technology（浙江工业大学信息工程学院）；Joint Laboratory of Industrial Intelligent Technologies, Russia, China（中俄工业智能技术联合实验室）；Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences（中国科学院宁波材料技术与工程研究所）；United Institute of Informatics Problems of the National Academy of Belarus（白俄罗斯国家科学院信息问题联合研究所）；Saint Petersburg Federal Research Center of the Russian Academy of Sciences（俄罗斯科学院圣彼得堡联邦科研中心）
This paper presents a new approach to recognize elements in floor plan layouts. Besides walls and rooms, we aim to recognize diverse floor plan elements, such as doors, windows and different types of rooms, in the floor layouts. To this end, we model a hierarchy of floor plan elements and design a deep multi-task neural network with two tasks: one to learn to predict room-boundary elements, and the other to predict rooms with types. More importantly, we formulate the room-boundary-guided attention mechanism in our spatial contextual module to carefully take room-boundary features into account …
Floorplan-SLAM: A Real-Time, High-Accuracy, and Long-Term Multi-Session Point-Plane SLAM for Efficient Floorplan Reconstruction
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所多模态人工智能系统国家重点实验室）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；College of Information Science and Technology, Beijing University of Chemical Technology（北京化工大学信息科学与技术学院）
Graz University of Technology（格拉茨技术大学）；École des Ponts ParisTech（巴黎高科路桥学院）
We propose a novel method for reconstructing floor plans from noisy 3D point clouds. Our main contribution is a principled approach that relies on the Monte Carlo Tree Search (MCTS) algorithm to maximize a suitable objective function efficiently despite the complexity of the problem. Like previous work, we first project the input point cloud to a top view to create a density map and extract room proposals from it. Our method selects and optimizes the polygonal shapes of these room proposals jointly to fit the density map and outputs an accurate vectorized floor map even for large complex scene…
Avon Old Farms School（埃文老农场中学）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）
Recognition of floor plans has been a challenging and popular task. Despite that many recent approaches have been proposed for this task, they typically fail to make the room-level unified prediction. Specifically, multiple semantic categories can be assigned in a single room, which seriously limits their visual quality and applicability. In this paper, we propose a novel approach to recognize the floor plan layouts with a newly proposed Offset-Guided Attention mechanism to improve the semantic consistency within a room. In addition, we present a Feature Fusion Attention module that leverages …
ShanghaiTech University（上海科技大学）；Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences（中国科学院上海微系统与信息技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Shanghai Engineering Research Center of Intelligent Vision and Imaging（上海智能视觉与成像工程研究中心）
We present a novel framework for floor plan-based, full six degree-of-freedom LiDAR localization. Our approach relies on robust ceiling and ground plane detection, which solves part of the pose and supports the segmentation of vertical structure elements such as walls and pillars. Our core contribution is a novel nearest neighbour data structure for an efficient look-up of nearest vertical structure elements from the floor plan. The registration is realized as a pair-wise regularized windowed pose graph optimization. Highly efficient, accurate and drift-free long-term localization is demonstra…
FR-SLAM: A SLAM Improvement Method Based on Floor Plan Registration
Suzhou Campus Southeast University（东南大学苏州校区）；Nanjing center for applied mathematics（南京应用数学中心）；School of Automation（自动化学院）；School of Cyber Science and Engineering（网络科学与工程学院）；Shenzhen Research Institute Southeast University（东南大学深圳研究院）；Samsung Electronics（三星电子）；Samsung Electronics(China) R&D Center（三星电子（中国）研发中心）
In this paper, we propose SUGAMAN (Supervised and Unified framework using Grammar and Annotation Model for Access and Navigation). SUGAMAN is a Hindi word meaning "easy passage from one place to another". SUGAMAN synthesizes textual description from a given floor plan image for the visually impaired. A visually impaired person can navigate in an indoor environment using the textual description generated by SUGAMAN. With the help of a text reader software, the target user can understand the rooms within the building and arrangement of furniture to navigate. SUGAMAN is the first framework for de…
Text-Aided Multi-Modal Panoptic Symbol Spotting for CAD Floor Plan Drawings
CCSE Lab, Beihang University（北京航空航天大学CCSE实验室）；School of Transportation Science and Engineering, Beihang University（北京航空航天大学交通科学与工程学院）；The Hong Kong Polytechnic University（香港理工大学）
IHome Company（IHome公司）；IBM Research Singapore（IBM新加坡研究院）；Radio Company（Radio公司）；Huazhong University of Science and Technology（华中科技大学）；Tongji University（同济大学）
In this paper, we propose an end-end model for producing furniture layout for interior scene synthesis from the random vector. This proposed model is aimed to support professional interior designers to produce the interior decoration solutions more quickly. The proposed model combines a conditional floor-plan module of the room, a conditional graphical floor-plan module of the room and a conditional layout module. As compared with the prior work on scene synthesis, our proposed three modules enhance the ability of auto-layout generation given the dimensional category of the room. We conduct ou…
National Tsing Hua University（台湾清华大学）；Phiar Technologies（Phiar科技公司）
We present 360-DFPE, a sequential floor plan estimation method that directly takes 360-images as input without relying on active sensors or 3D information. Our approach leverages a loosely coupled integration between a monocular visual SLAM solution and a monocular 360-room layout approach, which estimate camera poses and layout geometries, respectively. Since our task is to sequentially capture the floor plan using monocular images, the entire scene structure, room instances, and room shapes are unknown. To tackle these challenges, we first handle the scale difference between visual odometry …
University of Freiburg（弗莱堡大学）；Toyota Research Institute（丰田研究院）
Indoor localization is one of the crucial enablers for deployment of service robots. Although several successful techniques for indoor localization have been proposed, the majority of them relies on maps generated from data gathered with the same sensor modality used for localization. Typically, tedious labor by experts is needed to acquire this data, thus limiting the readiness of the system as well as its ease of installation for inexperienced operators. In this paper, we propose a memory and computationally efficient monocular camera-based localization system that allows a robot to estimate…
Tell2Design: A Dataset for Language-Guided Floor Plan Generation
Singapore University of Technology and Design（新加坡科技设计大学）；Institute of High Performance Computing (IHPC), A*STAR（新加坡科技研究局高性能计算研究所）；National University of Singapore（新加坡国立大学）
University of Mauritius（毛里求斯大学）；University of Essex（埃塞克斯大学）；Chesteroc ltd (Mundocom Mauritius)（切斯特克有限公司（毛里求斯蒙多科姆））
Nowadays three dimension (3D) architectural visualisation has become a powerful tool in the conceptualisation, design and presentation of architectural products in the construction industry, providing realistic interaction and walkthrough on engineering products. Traditional ways of implementing 3D models involves the use of specialised 3D authoring tools along with skilled 3D designers with blueprints of the model and this is a slow and laborious process. The aim of this paper is to automate this process by simply analyzing the blueprint document and generating the 3D scene automatically. For…
Brown University（布朗大学）；Simon Fraser University（西蒙弗雷泽大学）
Realistic 3D indoor scene datasets have enabled significant recent progress in computer vision, scene understanding, autonomous navigation, and 3D reconstruction. But the scale, diversity, and customizability of existing datasets is limited, and it is time-consuming and expensive to scan and annotate more. Fortunately, combinatorics is on our side: there are enough individual rooms in existing 3D scene datasets, if there was but a way to recombine them into new layouts. In this paper, we propose the task of generating novel 3D floor plans from existing 3D rooms. We identify three sub-tasks of …
University of Zurich（苏黎世大学）；ETH Zürich（苏黎世联邦理工学院）；University College London（伦敦大学学院）；Adobe Research（奥多比研究中心）
Recent years have seen a proliferation of new digital products for the efficient management of indoor spaces, with important applications like emergency management, virtual property showcasing and interior design. These products rely on accurate 3D models of the environments considered, including information on both architectural and non-permanent elements. These models must be created from measured data such as RGB-D images or 3D point clouds, whose capture and consolidation involves lengthy data workflows. This strongly limits the rate at which 3D models can be produced, preventing the adopt…
Aalborg University（奥尔堡大学）；Software Radio Systems（软件无线电系统公司）
Environmental scene reconstruction is of great interest for autonomous robotic applications, since an accurate representation of the environment is necessary to ensure safe interaction with robots. Equally important, it is also vital to ensure reliable communication between the robot and its controller. Large Intelligent Surface (LIS) is a technology that has been extensively studied due to its communication capabilities. Moreover, due to the number of antenna elements, these surfaces arise as a powerful solution to radio sensing. This paper presents a novel method to translate radio environme…
3D Scene Graph Prediction: Generating Hierarchical Models from Partially Observed Environments
Laboratory for Information & Decision Systems (LIDS), Massachusetts Institute of Technology（信息与决策系统实验室（LIDS），麻省理工学院）；Department of Electrical and Computer Engineering, Oakland University（奥克兰大学电气与计算机工程系）
Recognizing and Reconstructing a Multi-Unit Floor Plan
Department of Control and Instrumentation, Brno University of Technology, Brno, Czech Republic（控制与仪器系，布拉格技术大学，布拉格，捷克共和国）；Department of Software Technology, Faculty of Electrical Engineering Mathematics and Computer Science, TU Delft, Delft, Netherlands（软件技术系，电气工程数学与计算机科学学院，代尔夫特理工大学，代尔夫特，荷兰）；Department of Management in the Built Environment, Faculty of Architecture and the Built Environment, TU Delft, Delft, Netherlands（建筑环境管理系，建筑与环境学院，代尔夫特理工大学，代尔夫特，荷兰）；Institute for Research and Applications of Fuzzy Modeling, University of Ostrava, Ostrava, Czech Republic and with Department of Informatics, Mendel University in Brno, Brno, Czech Republic（模糊建模研究与应用研究所，奥斯特拉瓦大学，奥斯特拉瓦，捷克共和国，并与布拉格梅德勒大学信息系联合）；Department of Software Technology, Faculty of Electrical Engineering Mathematics and Computer Science, TU Delft, Delft, Netherlands and with Dependable and Scalable Software Systems, Institute of Systems Engineering, Faculty of Electrical Engineering and Computer Science, Leibniz University Hannover, Hannover, Germany（软件技术系，电气工程数学与计算机科学学院，代尔夫特理工大学，代尔夫特，荷兰，并与可靠和可扩展软件系统，系统工程研究所，电气工程与计算机科学学院，莱比锡大学汉诺威分校，汉诺威，德国）
We propose 4 insights that help to significantly improve the performance of deep learning models that predict surface normals and semantic labels from a single RGB image. These insights are: (1) denoise the "ground truth" surface normals in the training set to ensure consistency with the semantic labels; (2) concurrently train on a mix of real and synthetic data, instead of pretraining on synthetic and finetuning on real; (3) jointly predict normals and semantics using a shared model, but only backpropagate errors on pixels that have valid training labels; (4) slim down the model and use grays…
