用混合模型提升墙体分割精度，助力自动3D建模
Enhancing Floor Plan Recognition: A Hybrid Mix-Transformer and U-Net Approach for Precise Wall Segmentation
- 结合Mix-Transformer与U-Net，融合全局语义与细节特征
- 在CubiCasa5k和区域数据集上边界准确率显著优于基准模型
- 适合需要高精度墙体分割的3D重建研究者使用
从2D平面图自动重建室内三维空间需高精度语义分割结构元素，尤其是墙体。现有方法常难以检测细长结构且难以保持几何精度。为此，我们提出MitUNet，一种混合神经网络架构，旨在弥合全局语义上下文与细粒度结构细节之间的差距。该模型将Mix-Transformer编码器与增强空间与通道注意力块的U-Net解码器相结合，并采用Tversky损失函数优化，实现精确率与召回率的平衡，确保边界恢复准确。在CubiCasa5k数据集及区域数据集上的实验表明，MitUNet在生成结构正确掩码方面表现优异，边界准确性显著超越标准模型。该方法为自动化3D重建流程提供了可靠基础。为保证可复现性并促进后续研究，源代码与区域数据集已公开：https://github.com/aliasstudio/mitunet 及 https://doi.org/10.5281/zenodo.17871079。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。