mlsanityData to 14 Oct 2026

PanelNet: Understanding 360 Indoor Environment via Panel Representation

arXiv 2305.09078 ↗First posted 16 May 2023cs.CVcited by 19

Not on the map. Why?

Abstract (arXiv)

Indoor 360 panoramas have two essential properties. (1) The panoramas are continuous and seamless in the horizontal direction. (2) Gravity plays an important role in indoor environment design. By leveraging these properties, we present PanelNet, a framework that understands indoor environments using a novel panel representation of 360 images. We represent an equirectangular projection (ERP) as consecutive vertical panels with corresponding 3D panel geometry. To reduce the negative impact of panoramic distortion, we incorporate a panel geometry embedding network that encodes both the local and global geometric features of a panel. To capture the geometric context in room design, we introduce Local2Global Transformer, which aggregates local information within a panel and panel-wise global context. It greatly improves the model performance with low training overhead. Our method outperforms existing methods on indoor 360 depth estimation and shows competitive results against state-of-the-art approaches on the task of indoor layout estimation and semantic segmentation.

Key facts. Cited by 19 papers in the map (data through 14 Oct 2026). Builds on 34 of its 47 references that are in the map. First posted on arXiv 16 May 2023.

Builds on

34 of 47 references.

References · 34

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  5. 2021Vision Transformers for Dense Predictioncited by 1,803
  6. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,376
  7. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
  8. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,228
  9. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,101
  10. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 723
  11. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
  12. 2017Joint 2D-3D-Semantic Data for Indoor Scene Understandingcited by 406
22 more
  1. 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 403
  2. 2019Enforcing geometric constraints of virtual normal for depth predictioncited by 234
  3. 2019HorizonNet: Learning Room Layout with 1D Representation and Pano Stretch Data Augmentationcited by 108
  4. 2020HoHoNet: 360 Indoor Holistic Understanding with Latent Horizontal Featurescited by 105
  5. 2018OmniDepth: Dense Depth Estimation for Indoors Spherical Panoramascited by 99
  6. 2018LayoutNet: Reconstructing the 3D Room Layout from a Single RGB Imagecited by 95
  7. 2021UniFuse: Unidirectional Fusion for 360circ Panorama Depth Estimationcited by 92
  8. 2016Estimating Depth from Monocular Images as Classification Using Deep Fully Convolutional Residual Networkscited by 91
  9. 2019Spherical CNNs on Unstructured Gridscited by 79
  10. 2019Tangent Images for Mitigating Spherical Distortioncited by 79
  11. 2022Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentationcited by 72
  12. 2018DuLa-Net: A Dual-Projection Network for Estimating Room Layouts from a Single RGB Panoramacited by 68
  13. 2022OmniFusion: 360 Monocular Depth Estimation via Geometry-Aware Fusioncited by 61
  14. 2019DepthTransfer: Depth Extraction from Video Using Non-parametric Samplingcited by 60
  15. 2021360MonoDepth: High-Resolution 360deg Monocular Depth Estimationcited by 60
  16. 2021LED2-Net: Monocular 360 Layout Estimation via Differentiable Depth Renderingcited by 43
  17. 2018SpherePHD: Applying CNNs on a Spherical PolyHeDron Representation of 360 degree Imagescited by 41
  18. 2021ACDNet: Adaptively Combined Dilated Convolution for Monocular Panorama Depth Estimationcited by 39
  19. 2021DeepPanoContext: Panoramic 3D Scene Understanding with Holistic Scene Context Graph and Relation-based Optimizationcited by 33
  20. 2022LGT-Net: Indoor Panoramic Room Layout Estimation with Geometry-Aware Transformer Networkcited by 29
  21. 2019Pano Popups: Indoor 3D Reconstruction with a Plane-Aware Networkcited by 25
  22. 2019Mapped Convolutionscited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 8; 2025: 7; 2026: 3.

19 papers.

Sort:

  1. 2024Elite360D: Towards Efficient 360 Depth Estimation via Semantic- and Distance-Aware Bi-Projection Fusioncited by 31
  2. 2025A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Visioncited by 24
  3. 2024PanDA: Towards Panoramic Depth Anything with Unlabeled Panoramas and Mobius Spatial Augmentationcited by 22
  4. 2023PanoContext-Former: Panoramic Total Scene Understanding with a Transformercited by 19
  5. 2024Open Panoramic Segmentationcited by 17
  6. 2025Omnidirectional Multi-Object Trackingcited by 13
  7. 2024Multi-source Domain Adaptation for Panoramic Semantic Segmentationcited by 8
  8. 2025PanoSplatt3R: Leveraging Perspective Pretraining for Generalized Unposed Wide-Baseline Panorama Reconstructioncited by 8
  9. 2024Occlusion-Aware Seamless Segmentationcited by 7
  10. 2024Estimating Depth of Monocular Panoramic Image with Teacher-Student Model Fusing Equirectangular and Spherical Representationscited by 5
  11. 2025OmniTrack++: Omnidirectional Multi-Object Tracking by Learning Large-FoV Trajectory Feedbackcited by 4
  12. 2024Elite360M: Efficient 360 Multi-task Learning via Bi-projection Fusion and Cross-task Collaborationcited by 3
7 more
  1. 2025Panoramic Out-of-Distribution Segmentationcited by 2
  2. 2025360-Degree Full-view Image Segmentation by Spherical Convolution compatible with Large-scale Planar Pre-trained Modelscited by 1
  3. 2026Denoise and Align: Towards Source-Free UDA for Robust Panoramic Semantic Segmentationcited by 1
  4. 2026Panoramic Scene Understanding: A Survey from Distortion-Aware Engineering to Sphere-Native Modelingcited by 1
  5. 2024CUBE360: Learning Cubic Field Representation for Monocular 360 Depth Estimation for Virtual Realitycited by 0
  6. 2025PAGCNet: A Pose-Aware and Geometry Constrained Framework for Panoramic Depth Estimationcited by 0
  7. 2026Cross360: 360deg Monocular Depth Estimation via Cross Projections Across Scalescited by 0