mlsanityData to 14 Oct 2026

SphereDepth: Panorama Depth Estimation from Spherical Domain

arXiv 2208.13714 ↗First posted 29 Aug 2022cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

The panorama image can simultaneously demonstrate complete information of the surrounding environment and has many advantages in virtual tourism, games, robotics, etc. However, the progress of panorama depth estimation cannot completely solve the problems of distortion and discontinuity caused by the commonly used projection methods. This paper proposes SphereDepth, a novel panorama depth estimation method that predicts the depth directly on the spherical mesh without projection preprocessing. The core idea is to establish the relationship between the panorama image and the spherical mesh and then use a deep neural network to extract features on the spherical domain to predict depth. To address the efficiency challenges brought by the high-resolution panorama data, we introduce two hyper-parameters for the proposed spherical mesh processing framework to balance the inference speed and accuracy. Validated on three public panorama datasets, SphereDepth achieves comparable results with the state-of-the-art methods of panorama depth estimation. Benefiting from the spherical domain setting, SphereDepth can generate a high-quality point cloud and significantly alleviate the issues of distortion and discontinuity.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 37 of its 49 references that are in the map. First posted on arXiv 29 Aug 2022.

Builds on

37 of 49 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  5. 2021Vision Transformers for Dense Predictioncited by 1,803
  6. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
  7. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,376
  8. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
  9. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 820
  10. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 788
  11. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 782
  12. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 723
25 more
  1. 2020AdaBins: Depth Estimation using Adaptive Binscited by 601
  2. 2018Spherical CNNscited by 456
  3. 2017Joint 2D-3D-Semantic Data for Indoor Scene Understandingcited by 406
  4. 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 403
  5. 2020Consistent Video Depth Estimationcited by 220
  6. 2018High Quality Monocular Depth Estimation via Transfer Learningcited by 133
  7. 2019HorizonNet: Learning Room Layout with 1D Representation and Pano Stretch Data Augmentationcited by 108
  8. 2019Multi-Scale Geometric Consistency Guided Multi-View Stereocited by 105
  9. 2020HoHoNet: 360 Indoor Holistic Understanding with Latent Horizontal Featurescited by 105
  10. 2021Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Mergingcited by 104
  11. 2018OmniDepth: Dense Depth Estimation for Indoors Spherical Panoramascited by 99
  12. 2018LayoutNet: Reconstructing the 3D Room Layout from a Single RGB Imagecited by 95
  13. 2018MeshNet: Mesh Neural Network for 3D Shape Representationcited by 95
  14. 2021UniFuse: Unidirectional Fusion for 360circ Panorama Depth Estimationcited by 92
  15. 2020Towards Better Generalization: Joint Depth-Pose Learning without PoseNetcited by 85
  16. 2019Spherical CNNs on Unstructured Gridscited by 79
  17. 2019Tangent Images for Mitigating Spherical Distortioncited by 79
  18. 2018MeshCNN: A Network with an Edgecited by 69
  19. 2021Unsupervised Scale-consistent Depth Learning from Videocited by 69
  20. 2018Cube Padding for Weakly-Supervised Saliency Prediction in 360deg Videoscited by 66
  21. 2021Subdivision-Based Mesh Convolution Networkscited by 60
  22. 2019Corners for Layout: End-to-End Layout Recovery from 360 Imagescited by 55
  23. 2019Orientation-aware Semantic Segmentation on Icosahedron Spherescited by 53
  24. 2018SpherePHD: Applying CNNs on a Spherical PolyHeDron Representation of 360 degree Imagescited by 41
  25. 2018Self-Supervised Learning of Depth and Camera Motion from 360deg Videoscited by 40

Built on by

Cited by year (2026 to 14 Oct)

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

7 papers.

  1. 2025DA2: Depth Anything in Any Directioncited by 25
  2. 2024SphereUFormer: A U-Shaped Transformer for Spherical 360 Perceptioncited by 13
  3. 2024Estimating Depth of Monocular Panoramic Image with Teacher-Student Model Fusing Equirectangular and Spherical Representationscited by 5
  4. 2025SphereFusion: Efficient Panorama Depth Estimation via Gated Fusioncited by 2
  5. 2026From Perspective to Fisheye Depth Estimation and Open-Vocabulary Segmentationcited by 0
  6. 2026Decoupling Spherical Reasoning from Dense Prediction for 360 Depth Estimationcited by 0
  7. 2026SO(3)-RoPE for Spherical Transformerscited by 0