Architecture Engineers Award

Building Information Modeling (BIM) has become a central workflow in the architecture, engineering, and construction (AEC) industry, yet 2-dimensional (2D) architectural drawings remain indispensable for documentation, communication, and construction execution. Despite BIM’s advantages, generating 2D drawings from BIM models still requires substantial manual effort, with current practices demanding significant additional time for conversion. This research addresses this inefficiency by proposing an automated, deep learning–based framework capable of transforming BIM models into accurate and stylistically diverse 2D architectural drawings. Persistent Role of 2D Drawings in BIM-Based Workflows Although BIM offers rich parametric and information-embedded models, 2D drawings continue to dominate regulatory submissions, on-site coordination, and professional communication. The reliance on manual or semi-automated conversion processes introduces redundancy and inefficiency into BIM workfl...

  Architectural plan generation using pix2pix-series algorithms presents significant challenges, particularly regarding the absence of domain-specific evaluation standards and limited understanding of how training configurations jointly influence performance. Current architectural AI workflows focus heavily on visual output, often overlooking principle adherence, vectorization quality, and the structural logic of predicted plans. Addressing this gap, the proposed framework introduces a systematic experimental design and a dual-aspect evaluation approach specifically tailored for architectural-like plans, establishing a rigorous foundation for AI-enabled generative design in architecture. Limitations of Existing pix2pix Adaptations in Architectural Design Although pix2pix architectures are widely adopted for map translation and image-to-image tasks, their adaptation to architectural plan generation remains underdeveloped due to the lack of domain-centered evaluation benchmarks. A...

The evolution of architectural design is increasingly shaped by computational tools that support complex form exploration and performance-driven decision-making. Traditional form-finding methods are often limited by the designer’s manual iteration speed and the inability of existing machine learning models to generate structurally coherent, user-guided architectural forms. Emerging techniques, such as Stable Diffusion and Low-Rank Adaptation (LoRA), enable more efficient training and controlled generation of 3D morphological structures. By integrating heat-map-based geometry control with diffusion models, architects gain a powerful workflow for producing diverse design alternatives and achieving seamless transitions from conceptual forms to realistic renderings. This research situates itself within the broader framework of AI-assisted design and aims to expand the creative and technical capabilities of form-finding practices. Limitations of Existing Machine Learning Approaches in Form...

ArchiDiff represents a significant advancement in AI-driven architectural visualization by addressing the long-standing limitations of 3D reconstruction from 2D images. While traditional methods perform adequately with small or simple scenes, they often struggle to handle complex, large-scale architectural forms. ArchiDiff overcomes these challenges by integrating a curated architectural dataset, diffusion-based 3D generation, and interactive design tools that support early-stage architectural workflows. This platform enables architects to seamlessly convert images into accurate point-cloud forms and modify them instantly using intuitive 2D interactions. Architectural Design Challenges in Image-Based 3D Reconstruction 3D reconstruction from images in architecture remains limited due to occlusions, irregular geometries, and dense urban environments that complicate visual interpretation. Existing reconstruction pipelines typically fail to generalize to buildings with complex facades, ...

  The rapid evolution of AI in architecture is reshaping how early-stage design is conceptualized, analyzed, and communicated. Yet, despite its potential, the architectural industry still faces major obstacles in integrating AI into practical workflows. ArchiWeb emerges as a transformative web-based platform designed to bridge this gap by unifying data, processes, and computational intelligence. Its cloud-native, interactive environment supports lightweight data exchange and modular algorithms, enabling architects to embed AI-driven reasoning directly into conceptual design stages. By streamlining access to AI tools and fostering cross-disciplinary collaboration, ArchiWeb sets the foundation for a more intelligent, efficient, and environmentally responsible architectural future. The Need for Unified AI Integration in Architectural Practice Architectural workflows remain fragmented, especially when incorporating AI-based methods across varying stages of design. Traditional softw...

Advancements in computational design and digital fabrication are reshaping how architects and engineers approach sustainable building. Traditional construction often relies on standardized components, but bespoke geometries can improve performance, aesthetics, and usability. However, customized solutions usually demand specialized machinery and high costs, which limit accessibility in low-resource or remote settings. This research explores a novel fabrication method that leverages conventional Compressed Earth Block (CEB) presses with additively manufactured molds to produce customized blocks without increasing costs or environmental impact. Computational Design and Mass Customization Computational design has opened possibilities for creating complex, optimized geometries that improve both structural integrity and architectural aesthetics. Mass customization allows for the production of unique components at scale, but its practical application in construction remains limited due to ma...