mlsanityData to 7 Oct 2026

PSMNet: Position-aware Stereo Merging Network for Room Layout Estimation

arXiv 2203.15965 ↗First posted 30 Mar 2022cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose a new deep learning-based method for estimating room layout given a pair of 360 panoramas. Our system, called Position-aware Stereo Merging Network or PSMNet, is an end-to-end joint layout-pose estimator. PSMNet consists of a Stereo Pano Pose (SP2) transformer and a novel Cross-Perspective Projection (CP2) layer. The stereo-view SP2 transformer is used to implicitly infer correspondences between views, and can handle noisy poses. The pose-aware CP2 layer is designed to render features from the adjacent view to the anchor (reference) view, in order to perform view fusion and estimate the visible layout. Our experiments and analysis validate our method, which significantly outperforms the state-of-the-art layout estimators, especially for large and complex room spaces.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 16 of its 45 references that are in the map. First posted on arXiv 30 Mar 2022.

Builds on

16 of 45 references.

References · 16

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2017Squeeze-and-Excitation Networkscited by 4,763
  4. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 974
  5. 2019Structured3D: A Large Photo-realistic Dataset for Structured 3D Modelingcited by 285
  6. 2019HorizonNet: Learning Room Layout with 1D Representation and Pano Stretch Data Augmentationcited by 107
  7. 2020HoHoNet: 360 Indoor Holistic Understanding with Latent Horizontal Featurescited by 104
  8. 2018LayoutNet: Reconstructing the 3D Room Layout from a Single RGB Imagecited by 94
  9. 2018DuLa-Net: A Dual-Projection Network for Estimating Room Layouts from a Single RGB Panoramacited by 67
  10. 2021LED2-Net: Monocular 360 Layout Estimation via Differentiable Depth Renderingcited by 42
  11. 2017RoomNet: End-to-End Room Layout Estimationcited by 38
  12. 2018FloorNet: A Unified Framework for Floorplan Reconstruction from 3D Scanscited by 35
4 more
  1. 2019Floor-SP: Inverse CAD for Floorplans by Sequential Room-wise Shortest Pathcited by 35
  2. 2018Floorplan-Jigsaw: Jointly Estimating Scene Layout and Aligning Partial Scanscited by 11
  3. 2021SSLayout360: Semi-Supervised Indoor Layout Estimation from 360-Degree Panoramacited by 9
  4. 2021OmniLayout: Room Layout Reconstruction from Indoor Spherical Panoramascited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 2; 2024: 0; 2025: 3; 2026: 2.

10 papers.

  1. 2022High-Resolution Depth Estimation for 360-degree Panoramas through Perspective and Panoramic Depth Images Registrationcited by 10
  2. 2022GPR-Net: Multi-view Layout Estimation via a Geometry-aware Panorama Registration Networkcited by 10
  3. 2023Graph-CoVis: GNN-based Multi-view Panorama Global Pose Estimationcited by 8
  4. 2022360-MLC: Multi-view Layout Consistency for Self-training and Hyper-parameter Tuningcited by 4
  5. 2025Unposed Sparse Views Room Layout Reconstruction in the Age of Pretrain Modelcited by 3
  6. 2023U2RLE: Uncertainty-Guided 2-Stage Room Layout Estimationcited by 2
  7. 2025PixCuboid: Room Layout Estimation from Multi-view Featuremetric Alignmentcited by 2
  8. 2025PanoTPS-Net: Panoramic Room Layout Estimation via Thin Plate Spline Transformationcited by 0
  9. 2026ZeD-MAP: Bundle Adjustment Guided Zero-Shot Depth Maps for Real-Time Aerial Imagingcited by 0
  10. 2026PolyLayout: Multi-room Manhattan Layout Estimationcited by 0