The adoption of Building Information Modeling (BIM) is beneficial in
construction projects. However, it faces challenges due to the lack of a
unified and scalable framework for converting 3D model details into BIM. This
paper introduces SRBIM, a unified semantic reconstruction architecture for BIM
generation. Our approach's effectiveness is demonstrated through extensive
qualitative and quantitative evaluations, establishing a new paradigm for
automated BIM modeling.

本论文介绍了 SRBIM，这是一个统一的语义重建架构用于 BIM 生成，通过广泛的定性和定量评估证明了我们方法的有效性，为自动 BIM 建模建立了一个新的范式。

自动化生成 BIM 模型的追溯方法：建筑环境 3D 语义重建的统一框架

Towards Automating the Retrospective Generation of BIM Models: A Unified  Framework for 3D Semantic Reconstruction of the Built Environment

Like masked language modeling (MLM) in natural language processing, masked
image modeling (MIM) aims to extract valuable insights from image patches to
enhance the feature extraction capabilities of the underlying deep neural
network (DNN). Contrasted with other training paradigms like supervised
learning and unsupervised contrastive learning, masked image modeling (MIM)
pretraining typically demands significant computational resources in order to
manage large training data batches (e.g., 4096). The significant memory and
computation requirements pose a considerable challenge to its broad adoption.
To mitigate this, we introduce a novel learning framework,
termed~\textit{Block-Wise Masked Image Modeling} (BIM). This framework involves
decomposing the MIM tasks into several sub-tasks with independent computation
patterns, resulting in block-wise back-propagation operations instead of the
traditional end-to-end approach. Our proposed BIM maintains superior
performance compared to conventional MIM while greatly reducing peak memory
consumption. Moreover, BIM naturally enables the concurrent training of
numerous DNN backbones of varying depths. This leads to the creation of
multiple trained DNN backbones, each tailored to different hardware platforms
with distinct computing capabilities. This approach significantly reduces
computational costs in comparison with training each DNN backbone individually.
Our framework offers a promising solution for resource constrained training of
MIM.

我们引入了一种新的学习框架，即分块式遮蔽图像建模（BIM），用于解决遮蔽图像建模（MIM）的计算资源需求高的问题，并在保持卓越性能的同时大大降低内存消耗，同时实现多个深度不同的 DNN 骨干的并发训练，从而降低与单独训练每个 DNN 骨干相比的计算成本。这为资源受限的 MIM 训练提供了有前景的解决方案。

BIM: 基于块的自监督学习与图像模型掩膜

BIM: Block-Wise Self-Supervised Learning with Masked Image Modeling

This study explores the potential of generative artificial intelligence (AI)
models, specifically OpenAI's generative pre-trained transformer (GPT) series,
when integrated with building information modeling (BIM) tools as an
interactive design assistant for architectural design. The research involves
the development and implementation of three key components: 1) BIM2XML, a
component that translates BIM data into extensible markup language (XML)
format; 2) Generative AI-enabled Interactive Architectural design (GAIA), a
component that refines the input design in XML by identifying designer intent,
relevant objects, and their attributes, using pre-trained language models; and
3) XML2BIM, a component that converts AI-generated XML data back into a BIM
tool. This study validated the proposed approach through a case study involving
design detailing, using the GPT series and Revit. Our findings demonstrate the
effectiveness of state-of-the-art language models in facilitating dynamic
collaboration between architects and AI systems, highlighting the potential for
further advancements.

本研究探讨了 AI 生成模型，特别是 OpenAI 的生成预训练变压器（GPT）系列，当与建筑信息建模（BIM）工具集成为交互式设计助手时的潜力。研究通过开发和实施三个关键组成部分来完成，最终验证了该方法的有效性。

利用大型预训练语言模型和建筑信息模型进行交互式设计

Interactive Design by Integrating a Large Pre-Trained Language Model and  Building Information Modeling

Enhancing interoperability and information exchange between domain-specific
software products for BIM is an important aspect in the Architecture,
Engineering, Construction and Operations industry. Recent research started
investigating methods from the areas of machine and deep learning for semantic
enrichment of BIM models. However, training and evaluation of these machine
learning algorithms requires sufficiently large and comprehensive datasets.
This work presents IFCNet, a dataset of single-entity IFC files spanning a
broad range of IFC classes containing both geometric and semantic information.
Using only the geometric information of objects, the experiments show that
three different deep learning models are able to achieve good classification
performance.

提出了 IFCNet 数据集，通过使用几何信息进行实验，展示了三种不同的深度学习模型的分类性能，以提高建筑、工程、施工和运营行业中的 BIM 软件产品之间的互操作性和信息交换。