mlsanityData to 7 Oct 2026

Learning to Reconstruct 3D Non-Cuboid Room Layout from a Single RGB Image

arXiv 2104.07986 ↗First posted 16 Apr 2021cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Single-image room layout reconstruction aims to reconstruct the enclosed 3D structure of a room from a single image. Most previous work relies on the cuboid-shape prior. This paper considers a more general indoor assumption, i.e., the room layout consists of a single ceiling, a single floor, and several vertical walls. To this end, we first employ Convolutional Neural Networks to detect planes and vertical lines between adjacent walls. Meanwhile, estimating the 3D parameters for each plane. Then, a simple yet effective geometric reasoning method is adopted to achieve room layout reconstruction. Furthermore, we optimize the 3D plane parameters to reconstruct a geometrically consistent room layout between planes and lines. The experimental results on public datasets validate the effectiveness and efficiency of our method.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 25 of its 48 references that are in the map. First posted on arXiv 16 Apr 2021.

Builds on

25 of 48 references.

References · 25

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  4. 2015Fast R-CNNcited by 2,930
  5. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  6. 2019Objects as Pointscited by 1,172
  7. 2018CornerNet: Detecting Objects as Paired Keypointscited by 763
  8. 2019Structured3D: A Large Photo-realistic Dataset for Structured 3D Modelingcited by 285
  9. 2019HorizonNet: Learning Room Layout with 1D Representation and Pano Stretch Data Augmentationcited by 107
  10. 2018PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Imagecited by 105
  11. 2018LayoutNet: Reconstructing the 3D Room Layout from a Single RGB Imagecited by 94
  12. 2018PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Imagecited by 77
13 more
  1. 2019End-to-End Wireframe Parsingcited by 72
  2. 2020Learning to Parse Wireframes in Images of Man-Made Environmentscited by 71
  3. 2018DuLa-Net: A Dual-Projection Network for Estimating Room Layouts from a Single RGB Panoramacited by 67
  4. 2019Single-Image Piece-wise Planar 3D Reconstruction via Associative Embeddingcited by 56
  5. 2020Deep Hough-Transform Line Priorscited by 44
  6. 2019PPGNet: Learning Point-Pair Graph for Line Segment Detectioncited by 39
  7. 2017RoomNet: End-to-End Room Layout Estimationcited by 38
  8. 2017Physics Inspired Optimization on Semantic Transfer Features: An Alternative Method for Room Layout Estimationcited by 29
  9. 2020General 3D Room Layout from a Single View by Render-and-Comparecited by 21
  10. 2016A Coarse-to-Fine Indoor Layout Estimation (CFILE) Methodcited by 15
  11. 2020GeoLayout: Geometry Driven Room Layout Estimation Based on Depth Maps of Planescited by 12
  12. 2019Thinking Outside the Box: Generation of Unconstrained 3D Room Layoutscited by 10
  13. 2019Smart Hypothesis Generation for Efficient and Robust Room Layout Estimationcited by 10

Built on by

Cited by year

Citing papers per year: 2022: 4; 2023: 1; 2024: 1; 2025: 1.

7 papers.

  1. 2022Towards High-Fidelity Single-view Holistic Reconstruction of Indoor Scenescited by 43
  2. 2022Editable Indoor Lighting Estimationcited by 12
  3. 20223D Room Layout Estimation from a Cubemap of Panorama Image via Deep Manhattan Hough Transformcited by 11
  4. 2024Diorama: Unleashing Zero-shot Single-view 3D Indoor Scene Modelingcited by 10
  5. 2023Polygon Detection for Room Layout Estimation using Heterogeneous Graphs and Wireframescited by 6
  6. 2022Semantic Room Wireframe Detection from a Single Viewcited by 4
  7. 2025Unposed Sparse Views Room Layout Reconstruction in the Age of Pretrain Modelcited by 3