MitUNet: Enhancing Floor Plan Recognition using a Hybrid Mix-Transformer and U-Net Architecture
By: Dmitriy Parashchuk, Alexey Kapshitskiy, Yuriy Karyakin
Potential Business Impact:
Builds 3D rooms from flat blueprints accurately.
Automatic 3D reconstruction of indoor spaces from 2D floor plans requires high-precision semantic segmentation of structural elements, particularly walls. However, existing methods optimized for standard metrics often struggle to detect thin structural components and yield masks with irregular boundaries, lacking the geometric precision required for subsequent vectorization. To address this issue, we introduce MitUNet, a hybrid neural network architecture specifically designed for wall segmentation tasks in the context of 3D modeling. In MitUNet, we utilize a hierarchical Mix-Transformer encoder to capture global context and a U-Net decoder enhanced with scSE attention blocks for precise boundary recovery. Furthermore, we propose an optimization strategy based on the Tversky loss function to effectively balance precision and recall. By fine-tuning the hyperparameters of the loss function, we prioritize the suppression of false positive noise along wall boundaries while maintaining high sensitivity to thin structures. Our experiments on the public CubiCasa5k dataset and a proprietary regional dataset demonstrate that the proposed approach ensures the generation of structurally correct masks with high boundary accuracy, outperforming standard single-task models. MitUNet provides a robust tool for data preparation in automated 3D reconstruction pipelines.
Similar Papers
Advancing Brain Tumor Segmentation via Attention-based 3D U-Net Architecture and Digital Image Processing
CV and Pattern Recognition
Helps doctors find brain tumors better.
Comparative Study of UNet-based Architectures for Liver Tumor Segmentation in Multi-Phase Contrast-Enhanced Computed Tomography
CV and Pattern Recognition
Finds liver tumors in scans better than new methods.
IAUNet: Instance-Aware U-Net
CV and Pattern Recognition
Separates overlapping cells in medical images accurately