mlsanityData to 14 Oct 2026

Pano3D: A Holistic Benchmark and a Solid Baseline for 360o Depth Estimation

arXiv 2109.02749 ↗First posted 6 Sep 2021cs.CV cs.LGcited by 37

Not on the map. Why?

Abstract (arXiv)

Pano3D is a new benchmark for depth estimation from spherical panoramas. It aims to assess performance across all depth estimation traits, the primary direct depth estimation performance targeting precision and accuracy, and also the secondary traits, boundary preservation, and smoothness. Moreover, Pano3D moves beyond typical intra-dataset evaluation to inter-dataset performance assessment. By disentangling the capacity to generalize to unseen data into different test splits, Pano3D represents a holistic benchmark for 360o depth estimation. We use it as a basis for an extended analysis seeking to offer insights into classical choices for depth estimation. This results in a solid baseline for panoramic depth that follow-up works can build upon to steer future progress.

Key facts. Cited by 37 papers in the map (data through 14 Oct 2026). Builds on 38 of its 59 references that are in the map. First posted on arXiv 6 Sep 2021.

Builds on

38 of 59 references.

References · 38

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2016Densely Connected Convolutional Networkscited by 6,720
  4. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  5. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 2,010
  6. 2016Identity Mappings in Deep Residual Networkscited by 1,965
  7. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
  8. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,376
  9. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
  10. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 915
  11. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 820
  12. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 737
26 more
  1. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 723
  2. 2020AdaBins: Depth Estimation using Adaptive Binscited by 601
  3. 2017Progressive Neural Architecture Searchcited by 487
  4. 2018Gibson Env: Real-World Perception for Embodied Agentscited by 481
  5. 2017Joint 2D-3D-Semantic Data for Indoor Scene Understandingcited by 406
  6. 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 403
  7. 2019Structured3D: A Large Photo-realistic Dataset for Structured 3D Modelingcited by 286
  8. 2019Enforcing geometric constraints of virtual normal for depth predictioncited by 234
  9. 2018Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundariescited by 145
  10. 2018Evaluation of CNN-based Single-Image Depth Estimation Methodscited by 138
  11. 2019HorizonNet: Learning Room Layout with 1D Representation and Pano Stretch Data Augmentationcited by 108
  12. 2020HoHoNet: 360 Indoor Holistic Understanding with Latent Horizontal Featurescited by 105
  13. 2018OmniDepth: Dense Depth Estimation for Indoors Spherical Panoramascited by 99
  14. 2021UniFuse: Unidirectional Fusion for 360circ Panorama Depth Estimationcited by 92
  15. 2014Fast Edge Detection Using Structured Forestscited by 65
  16. 2020MatryODShka: Real-time 6DoF Video View Synthesis using Multi-Sphere Imagescited by 64
  17. 2020OASIS: A Large-Scale Dataset for Single Image 3D in the Wildcited by 62
  18. 2019Spherical View Synthesis for Self-Supervised 360 Depth Estimationcited by 51
  19. 2018Fast End-to-End Trainable Guided Filtercited by 50
  20. 2020Predicting Sharp and Accurate Occlusion Boundaries in Monocular Depth Estimation Using Displacement Fieldscited by 40
  21. 2019Indoor Depth Completion with Boundary Consistency and Self-Attentioncited by 29
  22. 2019Pano Popups: Indoor 3D Reconstruction with a Plane-Aware Networkcited by 25
  23. 2020ODE-CNN: Omnidirectional Depth Extension Networkscited by 18
  24. 2019Mapped Convolutionscited by 14
  25. 2021Single-Shot Cuboids: Geodesics-based End-to-end Manhattan Aligned Layout Estimation from Spherical Panoramascited by 7
  26. 2019Boundary Cues for 3D Object Shape Recoverycited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 9; 2023: 5; 2024: 8; 2025: 6; 2026: 8.

37 papers.

Sort:

  1. 2023EGformer: Equirectangular Geometry-biased Transformer for 360 Depth Estimationcited by 43
  2. 2025Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Cameracited by 40
  3. 2022Scalable and Equivariant Spherical CNNs by Discrete-Continuous (DISCO) Convolutionscited by 24
  4. 2025A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Visioncited by 24
  5. 2022Multi-Modal Masked Pre-Training for Monocular Panoramic Depth Completioncited by 23
  6. 2024PanDA: Towards Panoramic Depth Anything with Unlabeled Panoramas and Mobius Spatial Augmentationcited by 22
  7. 2023360BEV: Panoramic Semantic Mapping for Indoor Bird's-Eye Viewcited by 18
  8. 2024Pano2Room: Novel View Synthesis from a Single Indoor Panoramacited by 16
  9. 2022360 Depth Estimation in the Wild -- The Depth360 Dataset and the SegFuse Networkcited by 15
  10. 2024SphereUFormer: A U-Shaped Transformer for Spherical 360 Perceptioncited by 13
  11. 2026PanoVGGT: Feed-Forward 3D Reconstruction from Panoramic Imagerycited by 13
  12. 2022A Survey on RGB-D Datasetscited by 11
25 more
  1. 2023RigNet++: Semantic Assisted Repetitive Image Guided Network for Depth Completioncited by 11
  2. 2024SGFormer: Spherical Geometry Transformer for 360 Depth Estimationcited by 9
  3. 2026UniDAC: Universal Metric Depth Estimation for Any Cameracited by 8
  4. 2026Holo360D: A Large-Scale Real-World Dataset with Continuous Trajectories for Advancing Panoramic 3D Reconstruction and Beyondcited by 7
  5. 2022HiMODE: A Hybrid Monocular Omnidirectional Depth Estimation Modelcited by 6
  6. 2023S2Net: Accurate Panorama Depth Estimation on Spherical Surfacecited by 6
  7. 2024PanoNormal: Monocular Indoor 360deg Surface Normal Estimationcited by 6
  8. 2024Helvipad: A Real-World Dataset for Omnidirectional Stereo Depth Estimationcited by 6
  9. 2025RPG360: Robust 360 Depth Estimation with Perspective Foundation Models and Graph Optimizationcited by 4
  10. 2022Hybrid Skip: A Biologically Inspired Skip Connection for the UNet Architecturecited by 3
  11. 2022CPO: Change Robust Panorama to Point Cloud Localizationcited by 3
  12. 2022Neural Contourlet Network for Monocular 360 Depth Estimationcited by 3
  13. 2024SALVe: Semantic Alignment Verification for Floorplan Reconstruction from Sparse Panoramascited by 2
  14. 2025SphereFusion: Efficient Panorama Depth Estimation via Gated Fusioncited by 2
  15. 2025Depth Anything in 360^circ: Towards Scale Invariance in the Wildcited by 2
  16. 2026Genie Sim PanoWorld: An Infinite Indoor 3D World Generation Pipeline via Panoramic Scene Modeling and Simulationcited by 2
  17. 2022Cross-Domain Synthetic-to-Real In-the-Wild Depth and Normal Estimation for 3D Scene Understandingcited by 1
  18. 2023Calibrating Panoramic Depth Estimation for Practical Localization and Mappingcited by 1
  19. 2026CM-EVS: Sparse Panoramic RGB-D-Pose Data for Complete Scene Coveragecited by 1
  20. 2026DepthAgent: Towards Better Universal Depth Estimation via Sample-wise Expert Selectioncited by 1
  21. 2021A benchmark with decomposed distribution shifts for 360 monocular depth estimationcited by 0
  22. 2024PixRO: Pixel-Distributed Rotational Odometry with Gaussian Belief Propagationcited by 0
  23. 2025EfficientDepth: A Fast and Detail-Preserving Monocular Depth Estimation Modelcited by 0
  24. 2026Sphere-Depth: A Benchmark for Depth Estimation Methods with Varying Spherical Camera Orientationscited by 0
  25. 2026Decoupling Spherical Reasoning from Dense Prediction for 360 Depth Estimationcited by 0