PolyLayout: Multi-room Manhattan Layout Estimation

• URL: http://arxiv.org/abs/2608.03323v1
• Date: Tue, 04 Aug 2026 08:30:36 GMT
• Title: PolyLayout: Multi-room Manhattan Layout Estimation
• Abstract summary: Esting room layouts from multi-view imagery is a core task for indoor scene understanding.<n>We propose Poly, a multi-room layout estimation method that parameterizes room layouts as Manhattan 3D polygon features.<n>We introduce two new multi-view multi-room layout benchmarks by providing layout annotations to existing datasets.
• Score: 75.30995628543158
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Estimating room layouts from multi-view imagery is a core task for indoor scene understanding. Existing methods are typically limited either by poor generalization to new datasets or restrictive geometric assumptions of the room shape or camera configuration. Most also estimate rooms independently, failing to exploit shared building structure such as dominant directions, ground plane or ceiling height. We propose PolyLayout, a multi-room layout estimation method that parameterizes room layouts as Manhattan 3D polygons and optimizes them jointly across multiple rooms. The optimization objective is predicted by a neural network on top of robust pre-trained visual features and trained end-to-end with supervision only on output room layouts. At the same time, camera projection and polygon updates remain explicit and model-based. This separation between learned scoring and geometry improves generalization to new datasets and camera parameters. During optimization, PolyLayout adaptively refines the polygon topology through iterative wall split and merge operations while jointly utilizing structural cues across rooms. We introduce two new multi-view multi-room layout benchmarks by providing layout annotations to existing datasets, and experiments show that PolyLayout outperforms prior approaches, both in terms of accuracy and robustness. Project page: https://ghanning.github.io/PolyLayout

Related papers

• Z-FLoc: Zero-Shot Floorplan Localization via Geometric Primitives [72.63181031215858]
  We propose a zero-shot floorplan localization method that generalizes to novel environments without any retraining.<n>Our key insight is that dominant geometric primitives are ubiquitous in human-made environments.<n> Experiments on both simulated and real-world datasets show that our approach outperforms state-of-the-art learning-based methods on unseen environments.
  arXiv  Detail & Related papers  (2026-06-03T12:14:24Z)
• HouseLayout3D: A Benchmark and Training-Free Baseline for 3D Layout Estimation in the Wild [17.263404264950257]
  Current 3D layout estimation models are primarily trained on synthetic datasets containing simple single room or single floor environments.<n>We introduce House3D, a real world benchmark designed to support progress toward full building scale layout estimation.
  arXiv  Detail & Related papers  (2025-12-02T06:18:08Z)
• WorldMirror: Universal 3D World Reconstruction with Any-Prior Prompting [51.69408870574092]
  We present WorldMirror, an all-in-one, feed-forward model for versatile 3D geometric prediction tasks.<n>Our framework flexibly integrates diverse geometric priors, including camera poses, intrinsics, and depth maps.<n>WorldMirror achieves state-of-the-art performance across diverse benchmarks from camera, point map, depth, and surface normal estimation to novel view synthesis.
  arXiv  Detail & Related papers  (2025-10-12T17:59:09Z)
• PixCuboid: Room Layout Estimation from Multi-view Featuremetric Alignment [26.610824644310846]
  We introduce PixCuboid, an optimization-based approach for cuboid-shaped room layout estimation.<n>By training with the optimization end-to-end, we learn feature maps that yield large convergence basins and smooth loss landscapes.<n>In thorough experiments we validate our approach and significantly outperform the competition.
  arXiv  Detail & Related papers  (2025-08-06T17:27:50Z)
• 360 Layout Estimation via Orthogonal Planes Disentanglement and Multi-view Geometric Consistency Perception [56.84921040837699]
  Existing panoramic layout estimation solutions tend to recover room boundaries from a vertically compressed sequence, yielding imprecise results. We propose an orthogonal plane disentanglement network (termed DOPNet) to distinguish ambiguous semantics. We also present an unsupervised adaptation technique tailored for horizon-depth and ratio representations. Our solution outperforms other SoTA models on both monocular layout estimation and multi-view layout estimation tasks.
  arXiv  Detail & Related papers  (2023-12-26T12:16:03Z)
• Diagnostic Benchmark and Iterative Inpainting for Layout-Guided Image Generation [147.81509219686419]
  We propose a diagnostic benchmark for layout-guided image generation that examines four categories of spatial control skills: number, position, size, and shape. Next, we propose IterInpaint, a new baseline that generates foreground and background regions step-by-step via inpainting. We show comprehensive ablation studies on IterInpaint, including training task ratio, crop&paste vs. repaint, and generation order.
  arXiv  Detail & Related papers  (2023-04-13T16:58:33Z)
• Connecting the Dots: Floorplan Reconstruction Using Two-Level Queries [27.564355569013706]
  We develop a novel Transformer architecture that generates polygons of multiple rooms in parallel. Our method achieves a new state-of-the-art for two challenging datasets, Structured3D and SceneCAD. It can readily be extended to predict additional information, i.e., semantic room types and architectural elements like doors and windows.
  arXiv  Detail & Related papers  (2022-11-28T18:59:09Z)
• 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)
• RoomStructNet: Learning to Rank Non-Cuboidal Room Layouts From Single View [7.427006214471801]
  We present a new approach to estimate the layout of a room from its single image. Our approach learns an additional ranking function to estimate the final layout instead of using optimization. Our approach shows state-of-the-art results on standard datasets with mostly cuboidal layouts and also performs well on a dataset containing rooms with non-cuboidal layouts.
  arXiv  Detail & Related papers  (2021-10-01T20:42:49Z)
• General 3D Room Layout from a Single View by Render-and-Compare [36.94817376590415]
  We present a novel method to reconstruct the 3D layout of a room from a single perspective view. Our dataset consists of 293 images from ScanNet, which we annotated with precise 3D layouts.
  arXiv  Detail & Related papers  (2020-01-07T16:14:00Z)

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.