Objective

2

Indoor floor plan vectorization is a sophisticated technique aimed at extracting precise structural information from raster images and converting them into vector representations. This process is essential in fields such as architectural renovation， interior design， and scene understanding， where accurate and efficient vectorization of floor plans can greatly enhance the quality and usability of spatial data. Traditionally， the vectorization process has been carried out using a two-stage pipeline. In the first stage， deep neural networks are used to segment the raster image， producing masks that define the room regions within the floor plan. These masks serve as the foundation for the subsequent vectorization process. In the second stage， post-processing algorithms are applied to these masks to extract vector information， with a focus on elements such as walls， doors， and other structural components. However， this process is not without its challenges. One of the main issues is error accumulation； inaccuracies in the initial mask generation can lead to compounded errors during vectorization. Moreover， post-processing algorithms often lack robustness， particularly when dealing with complex or degraded input images， leading to suboptimal vectorization results.

Method

2

To address these challenges， we propose a novel approach based on diffusion models for vector reconstruction of indoor floor plans. Diffusion models， originally developed for generative tasks， have shown great promise in producing high-quality outputs by iteratively refining input data. Our method leverages this capability to enhance the precision of floor plan vectorization. Specifically， the algorithm starts with rough masks generated by object detection or instance segmentation models. While these masks provide a basic outline of the room regions， they may lack the accuracy needed for precise vectorization. The diffusion model is then employed to iteratively refine the contour points of these rough masks， gradually reconstructing the room contours with greater accuracy. This process involves multiple iterations， during which the model adjusts the contour points based on patterns learned from the training data， leading to a more accurate representation of the room boundaries. A key innovation in our approach is the introduction of a contour inclination loss function. This loss function is specifically designed to guide the diffusion model in generating more reasonable and structurally sound room layouts. By penalizing unrealistic or impractical contour inclinations， the model is encouraged to produce outputs that closely resemble real-world room configurations. This not only improves the visual accuracy of the room contours but also enhances the overall quality of the vectorized floor plan. The benefits of our diffusion model-based approach are manifold. Firstly， by refining room contours before the vectorization stage， we can significantly reduce the error accumulation that plagues traditional methods. The more accurate the room contours， the more precise the subsequent wall vector extraction will be. Secondly， the use of a diffusion model allows for more robust handling of complex or noisy input images. Unlike traditional post-processing algorithms， which may struggle with irregularities in the input data， the diffusion model's iterative refinement process is better equipped to address such challenges， leading to more reliable vectorization results.

Result

2

We have thoroughly validated our method on the public CubiCase5K dataset， a widely used benchmark in the field of floor plan vectorization. The results of our experiments demonstrate that our approach significantly outperforms existing methods in both accuracy and robustness. Notably， we observed a marked improvement in the precision of wall vector extraction， which is crucial for applications in architectural renovation and interior design. The diffusion model's ability to produce more accurate room contours directly translates into better vectorized representations of floor plans， making our approach an invaluable tool for professionals in these fields.

Conclusion

2

In conclusion， the vectorization of indoor floor plans is a critical task with far-reaching applications， and the limitations of traditional methods have highlighted the need for more advanced techniques. Our diffusion model-based algorithm represents a significant step forward， offering a more accurate and reliable solution for the vector reconstruction of indoor floor plans. By refining room contours through iterative adjustments and incorporating a contour inclination loss function， our method not only addresses the issue of error accumulation but also enhances the overall quality of the vectorized output. Furthermore， our method holds broad application prospects in the field of interior design. Modern interior designers increasingly rely on digital tools for design and planning， where accurate indoor space representation is essential. With our method， designers can quickly generate high-quality room outlines and apply them to various design scenarios， such as furniture placement， lighting design， and space optimization. This efficient and precise vectorization technology not only saves designers significant time but also improves the feasibility and practicality of design solutions. In the field of building renovation， our approach offers significant advantages as well. During the renovation of old buildings， it is often necessary to redraw and optimize the original floor plan. This process is often constrained by the quality of the original drawings， especially in older buildings， where the original plans may have deteriorated or been lost. Through our diffusion model vectorization method， architects can quickly reconstruct digital versions of these old floor plans and use them as a foundation for renovation designs. This not only improves the efficiency of the renovation process but also helps preserve the historical character of the building. Lastly， our method has important application potential in the field of architectural scene understanding. With the rise of smart homes and automated building management systems， accurate interior floor plan data is critical to enabling these intelligent features. Our vectorization method can generate highly accurate representations of indoor spaces， providing reliable foundational data for intelligent systems. Overall， our approach promises to significantly improve the efficiency and effectiveness of floor plan vectorization， paving the way for more accurate architectural designs and enhanced spatial understanding.