Diffusion Transformers for Roof Graph Synthesis and Reconstruction

• URL: http://arxiv.org/abs/2608.25652v1
• Date: Wed, 26 Aug 2026 11:32:16 GMT
• Title: Diffusion Transformers for Roof Graph Synthesis and Reconstruction
• Abstract summary: RoofDiT is a generative framework for 2D roof graph synthesis and reconstruction.<n>We show improved graph generation quality over a diffusion baseline, favorable performance against a straight-skeleton prior in the footprint-conditioned setting, and the highest edge F1 among compared methods for image-guided reconstruction.
• Score: 2.721477719641864
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present RoofDiT, a generative framework for 2D roof graph synthesis and reconstruction. Roofs are compactly described as planar graphs of junctions and structural edges, but existing methods often rely on fixed geometric rules or direct reconstruction objectives. RoofDiT instead models roof structures directly as vertex-edge graphs and learns a conditional generative prior over their geometry and connectivity. Our framework follows a two-stage design: a diffusion transformer generates roof vertices, and an edge prediction module infers the corresponding graph topology. To improve geometric fidelity, RoofDiT combines relative geometry-aware attention with footprint and aerial-image conditioning, while using an alignment regularizer to encourage common horizontal, vertical, and diagonal roof patterns. The same model supports unconditional generation, footprint-conditioned synthesis, and image-guided reconstruction by changing the conditioning signal. Experiments show improved graph generation quality over a diffusion baseline, favorable performance against a straight-skeleton prior in the footprint-conditioned setting, and the highest edge F1 among compared methods for image-guided reconstruction.

Related papers

• Stable and Scalable Bundle Adjustment of Holistic 3D Structures [99.03818732955783]
  We present a new version of Bundle Adjustment (BA) for 3D computer vision.<n>BA is developed to jointly optimize cameras, poses and 3D points.<n>By group-induced measurements and cross-feature reprojection, we preserve the sparsity of classical point-only 3D regularization.
  arXiv  Detail & Related papers  (2026-09-03T16:08:03Z)
• Beyond Point-Wise Matching: Structural Representation Alignment for Accelerating Diffusion Transformers [93.3976834364707]
  We propose sREPA, a structural REPresentation Alignment framework to enforce consistency in the relational geometry of feature maps.<n>By encouraging the model to internalize holistic spatial layouts and structural correlations from pre-trained features, sREPA achieves faster and more stable convergence.
  arXiv  Detail & Related papers  (2026-05-16T12:01:04Z)
• HiDiGen: Hierarchical Diffusion for B-Rep Generation with Explicit Topological Constraints [11.721957326448162]
  Boundary representation (B-rep) is the standard 3D modeling format in CAD systems.<n>HiDiGen is a hierarchical generation framework that decouples geometry modeling into two stages.<n> Experimental results show that HiDiGen achieves strong performance, generating novel, diverse, and topologically sound CAD models.
  arXiv  Detail & Related papers  (2026-04-03T08:06:51Z)
• GFLAN: Generative Functional Layouts [1.1458853556386797]
  GFLAN is a generative framework that restructures floor plan synthesis through explicit factorization into topological planning and geometric realization.<n>Our approach departs from direct pixel-to-pixel or wall-tracing generation in favor of a principled two-stage decomposition.
  arXiv  Detail & Related papers  (2025-12-18T07:52:47Z)
• Aligned Novel View Image and Geometry Synthesis via Cross-modal Attention Instillation [62.87088388345378]
  We introduce a diffusion-based framework that performs aligned novel view image and geometry generation via a warping-and-inpainting methodology.<n>Method leverages off-the-shelf geometry predictors to predict partial geometries viewed from reference images.<n>Cross-modal attention distillation is proposed to ensure accurate alignment between generated images and geometry.
  arXiv  Detail & Related papers  (2025-06-13T16:19:00Z)
• SeaDAG: Semi-autoregressive Diffusion for Conditional Directed Acyclic Graph Generation [83.52157311471693]
  We introduce SeaDAG, a semi-autoregressive diffusion model for conditional generation of Directed Acyclic Graphs (DAGs) Unlike conventional autoregressive generation that lacks a global graph structure view, our method maintains a complete graph structure at each diffusion step. We explicitly train the model to learn graph conditioning with a condition loss, which enhances the diffusion model's capacity to generate realistic DAGs.
  arXiv  Detail & Related papers  (2024-10-21T15:47:03Z)
• GSDiff: Synthesizing Vector Floorplans via Geometry-enhanced Structural Graph Generation [3.78198085695976]
  architectural floorplan design is vital for housing and interior design, offering a faster, cost-effective alternative to manual sketches by architects.<n>Existing methods, including rule-based and learning-based approaches, face challenges in design and constrained generation with extensive post-processing.<n>We propose a novel generative framework for vector design via structural graph generation, called GSDiff.
  arXiv  Detail & Related papers  (2024-08-29T04:40:31Z)
• Graph Transformer GANs with Graph Masked Modeling for Architectural Layout Generation [153.92387500677023]
  We present a novel graph Transformer generative adversarial network (GTGAN) to learn effective graph node relations. The proposed graph Transformer encoder combines graph convolutions and self-attentions in a Transformer to model both local and global interactions. We also propose a novel self-guided pre-training method for graph representation learning.
  arXiv  Detail & Related papers  (2024-01-15T14:36:38Z)
• Curve Your Attention: Mixed-Curvature Transformers for Graph Representation Learning [77.1421343649344]
  We propose a generalization of Transformers towards operating entirely on the product of constant curvature spaces. We also provide a kernelized approach to non-Euclidean attention, which enables our model to run in time and memory cost linear to the number of nodes and edges.
  arXiv  Detail & Related papers  (2023-09-08T02:44:37Z)
• Roof-GAN: Learning to Generate Roof Geometry and Relations for Residential Houses [37.6686237027665]
  Roof-GAN is a novel generative adversarial network that generates structured geometry of residential roof structures as a set of roof primitives and their relationships. The generator produces a structured roof model as a graph, which consists of 1) primitive geometry as images at each node, 2) inter-primitive colinear/coplanar relationships at each edge, and 3) primitive geometry in a vector format at each node. The discriminator is trained to assess the primitive geometry, the primitive relationships, and the primitive vector geometry in a fully end-to-end architecture.
  arXiv  Detail & Related papers  (2020-12-17T00:47:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.