mlsanityData to 7 Oct 2026

PanoFormer: Panorama Transformer for Indoor 360 Depth Estimation

arXiv 2203.09283 ↗First posted 17 Mar 2022cs.CVcited by 94

Not on the map. Why?

Abstract (arXiv)

Existing panoramic depth estimation methods based on convolutional neural networks (CNNs) focus on removing panoramic distortions, failing to perceive panoramic structures efficiently due to the fixed receptive field in CNNs. This paper proposes the panorama transformer (named PanoFormer) to estimate the depth in panorama images, with tangent patches from spherical domain, learnable token flows, and panorama specific metrics. In particular, we divide patches on the spherical tangent domain into tokens to reduce the negative effect of panoramic distortions. Since the geometric structures are essential for depth estimation, a self-attention module is redesigned with an additional learnable token flow. In addition, considering the characteristic of the spherical domain, we present two panorama-specific metrics to comprehensively evaluate the panoramic depth estimation models' performance. Extensive experiments demonstrate that our approach significantly outperforms the state-of-the-art (SOTA) methods. Furthermore, the proposed method can be effectively extended to solve semantic panorama segmentation, a similar pixel2pixel task. Code will be available.

Key facts. Cited by 94 papers in the map (data through 7 Oct 2026). Builds on 35 of its 45 references that are in the map. First posted on arXiv 17 Mar 2022.

Builds on

35 of 45 references.

References · 35

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  5. 2021Vision Transformers for Dense Predictioncited by 1,789
  6. 2017Deformable Convolutional Networkscited by 1,481
  7. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,354
  8. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  9. 2021CvT: Introducing Convolutions to Vision Transformerscited by 946
  10. 2021Uformer: A General U-Shaped Transformer for Image Restorationcited by 864
  11. 2020AdaBins: Depth Estimation using Adaptive Binscited by 596
  12. 2016Semantic Scene Completion from a Single Depth Imagecited by 468
23 more
  1. 2018Spherical CNNscited by 452
  2. 2017Joint 2D-3D-Semantic Data for Indoor Scene Understandingcited by 404
  3. 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 402
  4. 2021Incorporating Convolution Designs into Visual Transformerscited by 248
  5. 2017Learning SO(3) Equivariant Representations with Spherical CNNscited by 244
  6. 2021LocalViT: Analyzing Locality in Vision Transformerscited by 228
  7. 2019HorizonNet: Learning Room Layout with 1D Representation and Pano Stretch Data Augmentationcited by 107
  8. 2020HoHoNet: 360 Indoor Holistic Understanding with Latent Horizontal Featurescited by 104
  9. 2018OmniDepth: Dense Depth Estimation for Indoors Spherical Panoramascited by 98
  10. 2021UniFuse: Unidirectional Fusion for 360circ Panorama Depth Estimationcited by 91
  11. 2021RigNet: Repetitive Image Guided Network for Depth Completioncited by 80
  12. 2019Tangent Images for Mitigating Spherical Distortioncited by 79
  13. 2019Spherical CNNs on Unstructured Gridscited by 76
  14. 2018Cube Padding for Weakly-Supervised Saliency Prediction in 360deg Videoscited by 66
  15. 2018Kernel Transformer Networks for Compact Spherical Convolutioncited by 56
  16. 2018SpherePHD: Applying CNNs on a Spherical PolyHeDron Representation of 360 degree Imagescited by 40
  17. 2019Monocular Depth Estimation: A Surveycited by 37
  18. 2017Learning Spherical Convolution for Fast Features from 360deg Imagerycited by 22
  19. 2021Improving 360 Monocular Depth Estimation via Non-local Dense Prediction Transformer and Joint Supervised and Self-supervised Learningcited by 19
  20. 2020ODE-CNN: Omnidirectional Depth Extension Networkscited by 18
  21. 2020Distortion-aware Monocular Depth Estimation for Omnidirectional Imagescited by 17
  22. 2018A Novel Approach to Quantized Matrix Completion Using Huber Loss Measurecited by 4
  23. 2018Snap Angle Prediction for 360circ Panoramascited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 7; 2023: 16; 2024: 20; 2025: 22; 2026: 29.

94 papers.

Sort:

By area:

  1. 2023Ctrl-Room: Controllable Text-to-3D Room Meshes Generation with Layout Constraintscited by 59
  2. 2022Review on Panoramic Imaging and Its Applications in Scene Understandingcited by 42
  3. 2023EGformer: Equirectangular Geometry-biased Transformer for 360 Depth Estimationcited by 42
  4. 2024Depth Anywhere: Enhancing 360 Monocular Depth Estimation via Perspective Distillation and Unlabeled Data Augmentationcited by 38
  5. 2025Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Cameracited by 38
  6. 2023HRDFuse: Monocular 360degDepth Estimation by Collaboratively Learning Holistic-with-Regional Depth Distributionscited by 37
  7. 2024Elite360D: Towards Efficient 360 Depth Estimation via Semantic- and Distance-Aware Bi-Projection Fusioncited by 31
  8. 2023SGAT4PASS: Spherical Geometry-Aware Transformer for PAnoramic Semantic Segmentationcited by 25
  9. 2025Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimationcited by 24
  10. 2022Multi-Modal Masked Pre-Training for Monocular Panoramic Depth Completioncited by 23
  11. 2025A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Visioncited by 23
  12. 2025DA2: Depth Anything in Any Directioncited by 22
38 more
  1. 2024PanDA: Towards Panoramic Depth Anything with Unlabeled Panoramas and Mobius Spatial Augmentationcited by 21
  2. 2023PanoContext-Former: Panoramic Total Scene Understanding with a Transformercited by 19
  3. 2023Single Frame Semantic Segmentation Using Multi-Modal Spherical Imagescited by 18
  4. 2023PanoSwin: a Pano-style Swin Transformer for Panorama Understandingcited by 18
  5. 2024Open Panoramic Segmentationcited by 17
  6. 2023Disentangling Orthogonal Planes for Indoor Panoramic Room Layout Estimation with Cross-Scale Distortion Awarenesscited by 14
  7. 2023Minimalist and High-Quality Panoramic Imaging with PSF-aware Transformerscited by 13
  8. 2022Cylin-Painting: Seamless 360textdegree Panoramic Image Outpainting and Beyondcited by 12
  9. 2022Complementary Bi-directional Feature Compression for Indoor 360deg Semantic Segmentation with Self-distillationcited by 12
  10. 2024SphereUFormer: A U-Shaped Transformer for Spherical 360 Perceptioncited by 12
  11. 2025Omnidirectional Multi-Object Trackingcited by 12
  12. 2025PANORAMA: The Rise of Omnidirectional Vision in the Embodied AI Eracited by 12
  13. 2023RigNet++: Semantic Assisted Repetitive Image Guided Network for Depth Completioncited by 11
  14. 2022High-Resolution Depth Estimation for 360-degree Panoramas through Perspective and Panoramic Depth Images Registrationcited by 10
  15. 2026One2Scene: Geometric Consistent Explorable 3D Scene Generation from a Single Imagecited by 10
  16. 2026PanoVGGT: Feed-Forward 3D Reconstruction from Panoramic Imagerycited by 10
  17. 2024SGFormer: Spherical Geometry Transformer for 360 Depth Estimationcited by 9
  18. 2025EDM: Equirectangular Projection-Oriented Dense Kernelized Feature Matchingcited by 7
  19. 2025PanoSplatt3R: Leveraging Perspective Pretraining for Generalized Unposed Wide-Baseline Panorama Reconstructioncited by 7
  20. 2025QuaDreamer: Controllable Panoramic Video Generation for Quadruped Robotscited by 7
  21. 2026UniDAC: Universal Metric Depth Estimation for Any Cameracited by 7
  22. 2024PanoNormal: Monocular Indoor 360deg Surface Normal Estimationcited by 6
  23. 2024Occlusion-Aware Seamless Segmentationcited by 6
  24. 2024Helvipad: A Real-World Dataset for Omnidirectional Stereo Depth Estimationcited by 6
  25. 2023Distortion-aware Transformer in 360deg Salient Object Detectioncited by 5
  26. 2023360 Layout Estimation via Orthogonal Planes Disentanglement and Multi-view Geometric Consistency Perceptioncited by 5
  27. 2024Estimating Depth of Monocular Panoramic Image with Teacher-Student Model Fusing Equirectangular and Spherical Representationscited by 5
  28. 2024Revisiting 360 Depth Estimation with PanoGabor: A New Fusion Perspectivecited by 5
  29. 2026MTPano: Multi-Task Panoramic Scene Understanding via Label-Free Integration of Dense Prediction Priorscited by 5
  30. 2026PanoWorld: Towards Spatial Supersensing in 360^circ Panorama Worldcited by 5
  31. 2024Mixed-View Panorama Synthesis using Geospatially Guided Diffusioncited by 4
  32. 2025RPG360: Robust 360 Depth Estimation with Perspective Foundation Models and Graph Optimizationcited by 4
  33. 2026PanoSAMic: Panoramic Image Segmentation from SAM Feature Encoding and Dual View Fusioncited by 4
  34. 2026More than the Sum: Panorama-Language Models for Adverse Omni-Scenescited by 4
  35. 2022HORIZON: High-Resolution Semantically Controlled Panorama Synthesiscited by 3
  36. 2023Deep Single Image Camera Calibration by Heatmap Regression to Recover Fisheye Images Under Manhattan World Assumptioncited by 3
  37. 2024Elite360M: Efficient 360 Multi-task Learning via Bi-projection Fusion and Cross-task Collaborationcited by 3
  38. 2024Multi-task Geometric Estimation of Depth and Surface Normal from Monocular 360deg Imagescited by 3

50 most cited of 94 All 94 (JSON)