Deep Learning and Data Engineering Approaches in Smart Building Decoration Automation: A Comprehensive Review

Abstract

With the rapid advancement of artificial intelligence and automation technologies, intelligent decoration automation has emerged as a transformative force in the construction and interior design industries. This review comprehensively explores the evolution, core technologies, and practical deployment of AI-driven automated building decoration systems. It first outlines the historical development trajectory of the industry, then systematically categorizes major machine learning algorithms—convolutional neural networks, generative adversarial networks, and reinforcement learning—analyzing their algorithmic foundations, typical applications, and key strengths and limitations. The paper also delves into the integration of AI with Building Information Modeling (BIM) and the Internet of Things (IoT), revealing how these technologies enable end-to-end intelligent platforms, enhance quality inspection, and optimize design and implementation processes. Extensive comparative evaluations of experimental and real-world outcomes demonstrate that intelligent automation significantly improves operational efficiency, defect detection accuracy, and economic benefits, while also exposing persistent bottlenecks related to data quality, system interoperability, user adaptability, and data ethics governance. Looking ahead, this paper identifies urgent research priorities, including developing adaptive and robust AI models, advancing multimodal perception and real-time feedback technologies, and establishing open benchmarking standards. This study aims to provide researchers and industry stakeholders with a technically rigorous and practical reference to support the continued advancement and responsible deployment of intelligent building finishing automation.