# OmniLayout: Room Layout Reconstruction from Indoor Spherical Panoramas

arXiv: https://arxiv.org/abs/2104.09403 · HTML: https://mlsanity.com/paper/2104.09403/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 34 references that are in the map.
- First posted on arXiv 19 Apr 2021.

## Builds on (most cited first, 18 of 18)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Geometric deep learning on graphs and manifolds using mixture model CNNs](https://mlsanity.com/paper/1611.08402/) (2016)
- [Spherical CNNs](https://mlsanity.com/paper/1801.10130/) (2018)
- [Joint 2D-3D-Semantic Data for Indoor Scene Understanding](https://mlsanity.com/paper/1702.01105/) (2017)
- [Clebsch-Gordan Nets: a Fully Fourier Space Spherical Convolutional Neural Network](https://mlsanity.com/paper/1806.09231/) (2018)
- [HorizonNet: Learning Room Layout with 1D Representation and Pano Stretch Data Augmentation](https://mlsanity.com/paper/1901.03861/) (2019)
- [HoHoNet: 360 Indoor Holistic Understanding with Latent Horizontal Features](https://mlsanity.com/paper/2011.11498/) (2020)
- [LayoutNet: Reconstructing the 3D Room Layout from a Single RGB Image](https://mlsanity.com/paper/1803.08999/) (2018)
- [DuLa-Net: A Dual-Projection Network for Estimating Room Layouts from a Single RGB Panorama](https://mlsanity.com/paper/1811.11977/) (2018)
- [Corners for Layout: End-to-End Layout Recovery from 360 Images](https://mlsanity.com/paper/1903.08094/) (2019)
- [Physics Inspired Optimization on Semantic Transfer Features: An Alternative Method for Room Layout Estimation](https://mlsanity.com/paper/1707.00383/) (2017)
- [Pano2CAD: Room Layout From A Single Panorama Image](https://mlsanity.com/paper/1609.09270/) (2016)
- [A Coarse-to-Fine Indoor Layout Estimation (CFILE) Method](https://mlsanity.com/paper/1607.00598/) (2016)
- [Mapped Convolutions](https://mlsanity.com/paper/1906.11096/) (2019)
- [Predicting Complete 3D Models of Indoor Scenes](https://mlsanity.com/paper/1504.02437/) (2015)
- [Noisy Student Training using Body Language Dataset Improves Facial Expression Recognition](https://mlsanity.com/paper/2008.02655/) (2020)

## Built on by (most cited first, 8 of 8)

- [ODGS: 3D Scene Reconstruction from Omnidirectional Images with 3D Gaussian Splattings](https://mlsanity.com/paper/2410.20686/) (2024)
- [Disentangling Orthogonal Planes for Indoor Panoramic Room Layout Estimation with Cross-Scale Distortion Awareness](https://mlsanity.com/paper/2303.00971/) (2023)
- [PSMNet: Position-aware Stereo Merging Network for Room Layout Estimation](https://mlsanity.com/paper/2203.15965/) (2022)
- [360 Layout Estimation via Orthogonal Planes Disentanglement and Multi-view Geometric Consistency Perception](https://mlsanity.com/paper/2312.16268/) (2023)
- [360deg Image Perception with MLLMs: A Comprehensive Benchmark and a Training-Free Method](https://mlsanity.com/paper/2603.16179/) (2026)
- [Atlanta Scaled layouts from non-central panoramas](https://mlsanity.com/paper/2401.17058/) (2024)
- [You Need a Transition Plane: Bridging Continuous Panoramic 3D Reconstruction with Perspective Gaussian Splatting](https://mlsanity.com/paper/2504.09062/) (2025)
- [Semi-Supervised 360 Layout Estimation with Panoramic Collaborative Perturbations](https://mlsanity.com/paper/2503.01114/) (2025)

## Abstract (arXiv)

Given a single RGB panorama, the goal of 3D layout reconstruction is to estimate the room layout by predicting the corners, floor boundary, and ceiling boundary. A common approach has been to use standard convolutional networks to predict the corners and boundaries, followed by post-processing to generate the 3D layout. However, the space-varying distortions in panoramic images are not compatible with the translational equivariance property of standard convolutions, thus degrading performance. Instead, we propose to use spherical convolutions. The resulting network, which we call OmniLayout performs convolutions directly on the sphere surface, sampling according to inverse equirectangular projection and hence invariant to equirectangular distortions. Using a new evaluation metric, we show that our network reduces the error in the heavily distorted regions (near the poles) by approx 25 % when compared to standard convolutional networks. Experimental results show that OmniLayout outperforms the state-of-the-art by approx 4% on two different benchmark datasets (PanoContext and Stanford 2D-3D). Code is available at https://github.com/rshivansh/OmniLayout.