PlanCraft: Sketch, Refine, and Furnish for Architect-Inspired Progressive 3D Residential Scene Generation

• URL: http://arxiv.org/abs/2607.23491v1
• Date: Sun, 26 Jul 2026 06:35:14 GMT
• Title: PlanCraft: Sketch, Refine, and Furnish for Architect-Inspired Progressive 3D Residential Scene Generation
• Abstract summary: 2D floor plan is not an optional intermediate but an irreplaceable spatial contract.<n>PlanCraft-Diff progressively sharpens an incomplete sketch into a geometrically precise, vectorizable floor plan.<n>PlanCraft-Agent then furnishes the scene within well-defined room boundaries.
• Score: 13.713464466502638
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Two structural insights have been overlooked in automated residential floor plan generation. First, design is inherently progressive. Architects begin with rough strokes and refine them over time, whereas existing methods typically require their conditioning representation to be fully specified before generation, a fundamental mismatch with how design actually works. Second, the 2D floor plan is not an optional intermediate but an irreplaceable spatial contract. Once room boundaries, doors, and windows are fixed, furnishing reduces from open-ended spatial reasoning to bounded constraint satisfaction. Bypassing this contract, as existing 3D systems do by delegating layout to language models, yields overlapping rooms and implausible proportions; directly calling general-purpose language models likewise produces geometrically invalid layouts. Guided by these insights, we present PlanCraft. SketchPlan supplies the missing training signal by replaying the architect's drawing process on 80K real floor plans, producing partial sketches at every completeness level. PlanCraft-Diff progressively sharpens an incomplete sketch into a geometrically precise, vectorizable floor plan through a coarse-to-fine strategy. With the spatial contract established, PlanCraft-Agent then furnishes the scene within well-defined room boundaries. Experiments show that PlanCraft achieves a 61.1\% lower FID than the best existing 2D method and surpasses existing 3D systems by 15 points in expert-rated spatial rationality, with a sketch at only 25\% completion already outperforming all fully specified baselines.

Related papers

• DPLAN: Minimal Connectivity to Floorplan Generation [0.42970700836450487]
  DPLAN (Door Connectivity to Floor Plan Generation) is a graph-based prototype that generates floor plans from door and non-adjacency constraints.<n>The framework is implemented in Python and includes a prototype for interactive constraint specification and floor plan visualization.
  arXiv  Detail & Related papers  (2026-06-19T06:51:56Z)
• Architect-Ant: Editable Automatic Furnishing of Architectural Floor Plans [73.84806303977797]
  We present Architect-Ant, an automatic furnishing framework powered by a fine-tuned vision-tuned model.<n>Furniture layouts are represented using a compact, coordinate-based domain-specific language (language) that encodes object placements.<n>We show that Architect-Ant produces geometrically valid and functionally plausible layouts, and suggest a scalable path for furnishing larger structure-only floor-plan datasets.
  arXiv  Detail & Related papers  (2026-06-09T14:55:43Z)
• HomeWorld: A Unified Floorplan-to-Furnished Framework for Generating Controllable, Densely Interactive Whole-Home Scenes [36.81011113715663]
  Indoor scene generation is crucial for robot simulation and modern interior design.<n>We propose a unified hierarchical framework that decomposes indoor scene synthesis into controllable stages.<n> Experiments and user studies demonstrate that our pipeline produces indoor spaces with greater layout diversity and stronger 3D design appeal.
  arXiv  Detail & Related papers  (2026-06-04T16:58:43Z)
• SceneAligner: 3D-Grounded Floorplan Localization in the Wild [24.114337264203428]
  We present an approach for performing floorplan localization in the wild by grounding the task in a reconstructed 3D representation of the scene.<n>Our method reconstructs a gravity-aligned 3D scene and projects it into a 2D density map that serves as a floorplan proxy.<n>To bridge the appearance gap between density maps and architectural floorplans, we adapt a 2D foundation model to learn cross-modal correspondences.
  arXiv  Detail & Related papers  (2026-05-21T14:53:05Z)
• WorldGrow: Generating Infinite 3D World [75.81531067447203]
  We tackle the challenge of generating the infinitely extendable 3D world -- large, continuous environments with coherent geometry and realistic appearance.<n>We propose WorldGrow, a hierarchical framework for unbounded 3D scene synthesis.<n>Our method features three core components: (1) a data curation pipeline that extracts high-quality scene blocks for training, making the 3D structured latent representations suitable for scene generation; (2) a 3D block inpainting mechanism that enables context-aware scene extension; and (3) a coarse-to-fine generation strategy that ensures both global layout plausibility and local geometric/textural fidelity.
  arXiv  Detail & Related papers  (2025-10-24T17:39:52Z)
• PLANA3R: Zero-shot Metric Planar 3D Reconstruction via Feed-Forward Planar Splatting [56.188624157291024]
  We introduce PLANA3R, a pose-free framework for metric Planar 3D Reconstruction from unposed two-view images.<n>Unlike prior feedforward methods that require 3D plane annotations during training, PLANA3R learns planar 3D structures without explicit plane supervision.<n>We validate PLANA3R on multiple indoor-scene datasets with metric supervision and demonstrate strong generalization to out-of-domain indoor environments.
  arXiv  Detail & Related papers  (2025-10-21T15:15:33Z)
• RAP: 3D Rasterization Augmented End-to-End Planning [104.52778241744522]
  Imitation learning for end-to-end driving trains policies only on expert demonstrations.<n>We propose 3D Rasterization, which replaces costly rendering with lightweightization of annotated primitives.<n>RAP achieves state-of-the-art closed-loop and long-tail robustness, ranking first on four major benchmarks.
  arXiv  Detail & Related papers  (2025-10-05T19:31:24Z)
• FloorplanMAE:A self-supervised framework for complete floorplan generation from partial inputs [25.35768485637194]
  We propose FloorplanMAE, a self-supervised learning framework for restoring incomplete floor plans into complete ones.<n>First, we developed a floor plan reconstruction dataset, FloorplanNet, specifically trained on architectural floor plans.<n> Secondly, we propose a floor plan reconstruction method based on Masked Autoencoders (MAE), which reconstructs missing parts by masking sections of the floor plan and training a lightweight Vision Transformer (ViT)
  arXiv  Detail & Related papers  (2025-06-10T02:22:05Z)
• PlanarSplatting: Accurate Planar Surface Reconstruction in 3 Minutes [32.00236197233923]
  PlanarSplatting is an ultra-fast and accurate surface reconstruction approach for multiview indoor images.<n>PlanarSplatting reconstructs an indoor scene in 3 minutes while having significantly better geometric accuracy.
  arXiv  Detail & Related papers  (2024-12-04T16:38:07Z)
• Neural 3D Scene Reconstruction with the Manhattan-world Assumption [58.90559966227361]
  This paper addresses the challenge of reconstructing 3D indoor scenes from multi-view images. Planar constraints can be conveniently integrated into the recent implicit neural representation-based reconstruction methods. The proposed method outperforms previous methods by a large margin on 3D reconstruction quality.
  arXiv  Detail & Related papers  (2022-05-05T17:59:55Z)
• 3D Sketch-aware Semantic Scene Completion via Semi-supervised Structure Prior [50.73148041205675]
  The goal of the Semantic Scene Completion (SSC) task is to simultaneously predict a completed 3D voxel representation of volumetric occupancy and semantic labels of objects in the scene from a single-view observation. We propose to devise a new geometry-based strategy to embed depth information with low-resolution voxel representation. Our proposed geometric embedding works better than the depth feature learning from habitual SSC frameworks.
  arXiv  Detail & Related papers  (2020-03-31T09:33:46Z)

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.