ArchComplete: Autoregressive 3D architectural design generation with hierarchical diffusion-based upsampling

Information

• Publication Type: Journal Paper (without talk)
• Workgroup(s)/Project(s):
  • Advanced Computational Design
• Date: December 2025
• Article Number: 104477
• DOI: 10.1016/j.cag.2025.104477
• ISSN: 1873-7684
• Journal: COMPUTERS & GRAPHICS-UK
• Pages: 12
• Volume: 133
• Publisher: PERGAMON-ELSEVIER SCIENCE LTD
• Keywords: Architectural Geometries, Geometric Deep Learning, Multiresolution Modeling, Shape Analysis and Synthesis, Shape Modeling Applications

Abstract

Recent advances in 3D generative models have shown promising results but often fall short in capturing the complexity of architectural geometries and topologies. To tackle this, we present ArchComplete, a two-stage voxel-based 3D generative pipeline consisting of a vector-quantized model, whose composition is modeled with an autoregressive transformer for generating coarse shapes, followed by a set of multiscale diffusion models for augmenting with fine geometric details. Key to our pipeline is (i) learning a contextually rich codebook of local patch embeddings, optimized alongside a 2.5D perceptual loss that captures global spatial correspondence of projections onto three axis-aligned orthogonal planes, and (ii) redefining upsampling as a set of multiscale conditional diffusion models learning over a hierarchy of coarse-to-fine local volumetric patches, with a guided denoising process using 3D Gaussian windows that smooths noise estimates across overlapping patches during inference. Trained on our introduced dataset of 3D house models, ArchComplete autoregressively generates models at the resolution of (Formula presented) and progressively refines them up to (Formula presented), with voxel sizes as small as (Formula presented). ArchComplete solves a variety of tasks, including genetic interpolation and variation, unconditional synthesis, shape and plan-drawing completion, as well as geometric detailization, while achieving state-of-the-art performance.

Additional Files and Images

Weblinks

• Entry in reposiTUm (TU Wien Publication Database)
• DOI: 10.1016/j.cag.2025.104477

BibTeX

@article{rasoulzadeh-2025-archcomplete,
  title =      "ArchComplete: Autoregressive 3D architectural design
               generation with hierarchical diffusion-based upsampling",
  author =     "Shervin Rasoulzadeh and Mathias Bank Stigsen and Iva Kovacic
               and Kristina Schinegger and Stefan Rutzinger and Michael
               Wimmer",
  year =       "2025",
  abstract =   "Recent advances in 3D generative models have shown promising
               results but often fall short in capturing the complexity of
               architectural geometries and topologies. To tackle this, we
               present ArchComplete, a two-stage voxel-based 3D generative
               pipeline consisting of a vector-quantized model, whose
               composition is modeled with an autoregressive transformer
               for generating coarse shapes, followed by a set of
               multiscale diffusion models for augmenting with fine
               geometric details. Key to our pipeline is (i) learning a
               contextually rich codebook of local patch embeddings,
               optimized alongside a 2.5D perceptual loss that captures
               global spatial correspondence of projections onto three
               axis-aligned orthogonal planes, and (ii) redefining
               upsampling as a set of multiscale conditional diffusion
               models learning over a hierarchy of coarse-to-fine local
               volumetric patches, with a guided denoising process using 3D
               Gaussian windows that smooths noise estimates across
               overlapping patches during inference. Trained on our
               introduced dataset of 3D house models, ArchComplete
               autoregressively generates models at the resolution of
               (Formula presented) and progressively refines them up to
               (Formula presented), with voxel sizes as small as (Formula
               presented). ArchComplete solves a variety of tasks,
               including genetic interpolation and variation, unconditional
               synthesis, shape and plan-drawing completion, as well as
               geometric detailization, while achieving state-of-the-art
               performance.",
  month =      dec,
  articleno =  "104477",
  doi =        "10.1016/j.cag.2025.104477",
  issn =       "1873-7684",
  journal =    "COMPUTERS & GRAPHICS-UK",
  pages =      "12",
  volume =     "133",
  publisher =  "PERGAMON-ELSEVIER SCIENCE LTD",
  keywords =   "Architectural Geometries, Geometric Deep Learning,
               Multiresolution Modeling, Shape Analysis and Synthesis,
               Shape Modeling Applications",
  URL =        "https://www.cg.tuwien.ac.at/research/publications/2025/rasoulzadeh-2025-archcomplete/",
}