Text-to-Floorplan Synthesis via Graph-Conditioned Diffusion Processes

Mobile robots, in modern technology, demand a more robust localization in a complex environment. Currently, the most commonly used 2D LiDAR localization system for mobile robots requires maps that are constructed by 2D SLAM. Such systems do not cope well with dynamic environments and also have high deployment costs when moving robots to a new environment setting as they require the reconstruction of a map for each new place. In modern days, a floor plan is indispensable for an indoor environment. It typically represents essential structures such as walls, corners, pillars, etc. for humans to navigate in the environment. This information turns out to be crucial for robot localization. In this paper, we propose an approach for 2D LiDAR localization in an architectural floor plan. We use partial simultaneous localization and mapping (PSLAM) algorithm to generate a map while we concurrently aligned it to the floor plan using Monte Carlo Localization (MCL) method. Real-world experiments have been conducted with our proposed method which results in robust robot localization, the algorithm is even evaluated on a large discrepancies floor plan (discrepancies between the floor plan and real-world). Our algorithm demonstrates that its capabilities of localizing in real-time applications.

The generation of floor plan layouts has been extensively studied in recent years, driven by the need for efficient and functional architectural designs. Despite significant advancements, existing methods often face limitations when dealing with specific input adjacency graphs or room shapes and boundary layouts. When adjacency graphs contain separating triangles, the floor plan must include rectilinear rooms (non-rectangular rooms with concave corners). From a design perspective, minimizing corners or bends in rooms is crucial for functionality and aesthetics. In this article, we present a Python-based application called G-Drawer for automatically generating floor plans with a minimum number of bends. G-Drawer takes any plane triangulated graph as an input and outputs a floor plan layout with minimum bends. It prioritizes generating a rectangular floor plan (RFP); if an RFP is not feasible, it then generates an orthogonal floor plan or an irregular floor plan. G-Drawer modifies orthogonal drawing techniques based on flow networks and applies them on the dual graph of a given PTG to generate the required floor plans. The results of this article demonstrate the efficacy of G-Drawer in creating efficient floor plans. However, in future, we need to work on generating multiple dimensioned floor plans having non-rectangular rooms as well as non-rectangular boundary. These enhancements will address both mathematical and architectural challenges, advancing the automated generation of floor plans toward more practical and versatile applications.

Modern automation demands mobile robots to be robustly localized in complex scenarios. Current localization systems typically use maps that require to be built and interpreted by experienced operators, increasing deployment costs as well as reducing the adaptability of robots to rearrangements in the environment. In contrast, architectural floor plans can be easily understood by non-expert users and typically represent only the non-rearrangeable parts of buildings. In this paper we propose a system for robot localization in architectural CAD drawings. Our method employs a simultaneous localization and mapping approach to online augment the floor plan with a map represented as a pose-graph with LiDAR measurements. Whenever the environment is accurately mapped in the vicinity of the robot, we use the graph to perform relative localization. We thoroughly evaluate our system in challenging real-world scenarios. Experiments demonstrate that our method is able to robustly track the robot pose even when the floor plan shows major discrepancies from the real-world. We show that our system achieves sub-centimeter accuracy and is suitable for real-time application.

Recently, indoor space construction information has been actively carried out primarily in large buildings and in underground facilities. However, the building of this data was done by only a handful of people, and it was a time- and money-intensive task. Therefore, the technology of automatically extracting a wall and constructing a 3D model from architectural floor plans was developed. Complete automation is still limited by accuracy issues, and only a few sets of floor plan data to which the technology can be applied exist. In addition, it is difficult to extract complicated walls and their thickness to build the wall-junction structure of indoor spatial information, which requires significant topological information in the automation process. In this paper, we propose an automatic method of extracting the wall from an architectural floor plan suitable for the restoration of the indoor spatial information according to the indoor spatial information standard.

This paper presents an automatic system for analyzing and labeling architectural floor plans. In order to detect the locations of the rooms, the proposed systems extracts both, structural and semantic information from given floor plans. Furthermore, OCR is applied on the text layer to retrieve the meaningful room labeling. Finally, a novel post-processing is proposed to split rooms into several sub-regions if several semantic rooms share the same physical room. Our fully automatic system is evaluated on a publicly available dataset of architectural floor plans. In our experiments, we could clearly outperform other state-of-the-art approaches for room detection.

Automatic analysis and sketch-based retrieval of architectural floor plans

The paper describes an intelligent computer aided architectural design system (ICAAD) called ICADS. ICADS encapsulates different types of design knowledge into independent "critic" modules. Each "critic" module possesses expertise in evaluating an architect's work in different areas of architectural design and can offer expert advice when needed. This research focuses on the representation of spatial information encoded in architectural floor plans and the representation of expert design knowledge. Described in the paper is our research in designing and developing two particular "critic" modules. The first module, FPDX, checks a residential apartment floor plan, verifies that the plan meets a set of government regulations, and offers suggestions for floor plan changes if regulations are not met. The second module, IDX, analyzes room and furniture layout according to a set of interior design guidelines and offers ideas on how furniture should be moved if the placement does not follow good design principles.

Most studies on map segmentation and recognition are focused on architectural floor plans, while there are very few analyses of shopping mall plans. The objective of the work is to accurately segment and recognize the shopping mall plan, obtaining location and semantic information for each room via segmentation and recognition. This work can be used in other applications such as indoor robot navigation, building area and location analysis, and three-dimensional reconstruction. First, we identify and match the catalog of a mall floor plan to obtain matching text, and then we use the two-stage region growth method we proposed to segment the preprocessed floor plan. The room number is then obtained by sending each segmented room section to an OCR (optical character recognition) system for identification. Finally, the system retrieves the matching text to match the room number in order to obtain the room name, and outputs the needed room location and semantic information. It is considered a successful detection when a room region can be successfully segmented and identified. The proposed method is evaluated on a dataset including 1340 rooms. Experimental results show that the accuracy of room segmentation is 92.54%, and the accuracy of room recognition is 90.56%. The total detection accuracy is 83.81%.

Spatial designers explore various design references in the design process. These design references significantly impact the quality of design outcomes and the process. Therefore, it is crucial to provide useful designs through the retrieval or generation process to spatial designers. To do this, a methodology must be developed to identify and quantify the floor plans multivariate design data. Through quantifying various design data, the retrieval and generation process can provide appropriate designs in many ways. This study proposed a new floor plan design framework for retrieval and generation with newly quantified design data. For validation of this framework, we conducted a floor plan retrieval and generation process. Newly quantified design data show usability in both processes. We also compare our framework with previous studies for validation. The comparison results show that our framework utilizes the most diverse design data of the floor plan.

As the market for indoor spatial information burgeons, the construction of indoor spatial databases consequently gain attention. Since floorplans are portable records of buildings, they are an indispensable source for the efficient construction of indoor environments. However, as previous research on floorplan information retrieval usually targeted specific formats, a system for constructing spatial information must include heuristic refinement steps. This study aims to convert diverse floorplans into an integrated format using the style transfer by deep networks. Our deep networks mimic a robust perception of human that recognize the cell structure of floorplans under various formats. The integrated format ensures that unified post-processing steps are required to the vectorization of floorplans. Through this process, indoor spatial information is constructed in a pragmatic way, using a plethora of architectural floorplans.

The recent years have seen the increasing importance of cognitive models for improved robot navigation. In this paper, a novel cognitive navigation package, which consists of topometric map representation and a three-level path planner, is proposed. The topometric maps are built from architectural floor plans with additional features within a limited number of selected regions. The inherent discrepancies between floor plans and the robot’s actual sensory readings are handled by the three-level path planner. The unique feature of this approach is that accurate localization is only required at the selected regions. At the other regions the robot will rely on the guiding directions towards the goal rather than on its accurate position on the map for navigation. Experiments show that our approach can endow a robot with capability for semantic interpretation and localization in unseen and dynamic environments.

Text-to-Image Person Retrieval (TIPR) aims to retrieve person images based on natural language descriptions. Although many TIPR methods have achieved promising results, sometimes textual queries cannot accurately and comprehensively reflect the content of the image, leading to poor cross-modal alignment and overfitting to limited datasets. Moreover, the inherent modality gap between text and image further amplifies these issues, making accurate cross-modal retrieval even more challenging. To address these limitations, we propose the Generation-Enhanced Alignment (GEA) from a generative perspective. GEA contains two parallel modules: 1) Text-Guided Token Enhancement (TGTE), which introduces diffusion-generated images as intermediate semantic representations to bridge the gap between text and visual patterns. These generated images enrich the semantic representation of text and facilitate cross-modal alignment. 2) Generative Intermediate Fusion (GIF) module, which combines cross-attention between generated images, original images, and text features to generate a unified representation optimized by triplet alignment loss. We conduct extensive experiments on three public TIPR datasets, CUHK-PEDES, RSTPReid, and ICFG-PEDES, to evaluate the performance of GEA. The remarkable results justify the efficacy of our method. More implementation details and extended results are available at https://github.com/sugelamyd123/Sup-for-GEA.

Vision–language models (VLMs) are increasingly used for the semantic interpretation of visual data, enabling flexible, open-vocabulary analysis of images based on natural language descriptions. These capabilities offer new opportunities for large-scale semantic mapping, particularly in domains where comprehensive labeled training data are scarce or difficult to obtain, such as agricultural and horticultural environments.Recent research has explored the transfer of semantic information from 2D imagery into three-dimensional representations, a process often called semantic lifting. This approach is attractive for outdoor scene understanding, as training native 3D vision–language models that generalize across landscapes and management regimes remains challenging and tools for 3D data are therefore not developed as far as in the 2D domain. However, most existing studies on semantic lifting focus on indoor environments or urban outdoor scenes, while agricultural landscapes—with their distinct structural characteristics, vegetation dynamics, and management patterns—remain underexplored.In this contribution, we investigate the applicability of open-vocabulary, VLM-based semantic lifting for large-scale 3D semantic mapping in agricultural settings. Building on insights from urban-scale benchmarks, we analyze how vision–language-driven semantic segmentation transfers to outdoor agricultural and horticultural scenes reconstructed from multi-view UAV imagery. Our results highlight both the potential of these models to generate spatially consistent semantic representations and their limitations, which are strongly dependent on land cover type and semantic classes.We discuss how such preliminary semantic 3D representations can support large-scale agroecosystem mapping and serve as an initial layer for downstream applications, including spatial analysis and the deployment of agricultural robotic systems. The findings provide guidance on the opportunities and current constraints of foundation-model-based semantic mapping for sustainable agricultural monitoring.

This paper describes the development of a constraint-based generative system (FSF system) to support the design of middle and high-rise apartment façades from architectural plans.Floor plan and façade designs are heavily interrelated, and, sometimes, the plan constrains the façade design during the design process.This relationship lends itself to apply constraint-based systems and we have designed the system to connect intelligently between apartment plan and façade.In our system, we define constraints into three categories: structural form, architectural style and function.We use genetic algorithm to generate plausible alternatives quickly and augmented by a constraint-based system, façades can be generated and modified much more easily in terms of real-time visual feedback for checking violence of the constraints and of dealing with updates smoothly through intelligent connecting plans to façades.

Semantic approaches present an efficient, detailed and easily understandable representation of knowledge from documents. Al-Quran contains a vast amount of knowledge that needs appropriate knowledge extraction. A semantic based approach can help in designing an efficient and explainable knowledge representation model for Al-Quran. This research aims to propose a semantic-graph knowledge representation model for verses of Al-Quran based on word dependencies. These features are used in the proposed knowledge representation model allowing the semantic graph matching to improve Al-Quran search applications' accuracy. The proposed knowledge representation model is essentially a formalism for generating a semantic graph representation of Quranic verses, which can be applied for knowledge base construction for other applications such as information retrieval system. A set of rules called Semantic Dependency Triple Rules are defined to be mapped into the semantic graph representing the verse's logic. The rules translate word dependencies and other NLP metadata into a triple form that holds logical information. The proposed model has been tested with English translation of Al-Quran on a document retrieval prototype The basic system has been enhanced with anaphoric pronouns correction, which has shown improvement in retrieval performance. The results have been compared with a closely related system and evaluated on the accuracy of the document retrieval in Precision, Recall and F-score measurements. The proposed model has achieved 65%, 60% and 62.4% for the measurements, respectively. It has also improved the overall accuracy of previous system by 43.8%.