mlsanityData to 7 Oct 2026

FoVA-Depth: Field-of-View Agnostic Depth Estimation for Cross-Dataset Generalization

arXiv 2401.13786 ↗First posted 24 Jan 2024cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

Wide field-of-view (FoV) cameras efficiently capture large portions of the scene, which makes them attractive in multiple domains, such as automotive and robotics. For such applications, estimating depth from multiple images is a critical task, and therefore, a large amount of ground truth (GT) data is available. Unfortunately, most of the GT data is for pinhole cameras, making it impossible to properly train depth estimation models for large-FoV cameras. We propose the first method to train a stereo depth estimation model on the widely available pinhole data, and to generalize it to data captured with larger FoVs. Our intuition is simple: We warp the training data to a canonical, large-FoV representation and augment it to allow a single network to reason about diverse types of distortions that otherwise would prevent generalization. We show strong generalization ability of our approach on both indoor and outdoor datasets, which was not possible with previous methods.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 33 of its 51 references that are in the map. First posted on arXiv 24 Jan 2024.

Builds on

33 of 51 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  3. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  4. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,354
  5. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  6. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 780
  7. 2021KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3Dcited by 570
  8. 2018Spherical CNNscited by 452
  9. 2020Modular Primitives for High-Performance Differentiable Renderingcited by 439
  10. 20193D Packing for Self-Supervised Monocular Depth Estimationcited by 437
  11. 2019Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matchingcited by 414
  12. 2017Joint 2D-3D-Semantic Data for Indoor Scene Understandingcited by 404
21 more
  1. 2017End-to-End Learning of Geometry and Context for Deep Stereo Regressioncited by 359
  2. 2018DeepMVS: Learning Multi-view Stereopsiscited by 277
  3. 2017Learning SO(3) Equivariant Representations with Spherical CNNscited by 244
  4. 2019Group-wise Correlation Stereo Networkcited by 235
  5. 2019Cost Volume Pyramid Based Depth Inference for Multi-View Stereocited by 154
  6. 2019Deep Stereo using Adaptive Thin Volume Representation with Uncertainty Awarenesscited by 151
  7. 2021TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformerscited by 117
  8. 2018OmniDepth: Dense Depth Estimation for Indoors Spherical Panoramascited by 98
  9. 2018Cube Padding for Weakly-Supervised Saliency Prediction in 360deg Videoscited by 66
  10. 2021360MonoDepth: High-Resolution 360deg Monocular Depth Estimationcited by 60
  11. 2018Kernel Transformer Networks for Compact Spherical Convolutioncited by 56
  12. 2022MVSFormer: Multi-View Stereo by Learning Robust Image Features and Temperature-based Depthcited by 50
  13. 2019Normal Assisted Stereo Depth Estimationcited by 49
  14. 2022Review on Panoramic Imaging and Its Applications in Scene Understandingcited by 42
  15. 2019360SD-Net: 360deg Stereo Depth Estimation with Learnable Cost Volumecited by 40
  16. 2021Generalized Binary Search Network for Highly-Efficient Multi-View Stereocited by 32
  17. 2019SweepNet: Wide-baseline Omnidirectional Depth Estimationcited by 24
  18. 2018Omnidirectional CNN for Visual Place Recognition and Navigationcited by 22
  19. 2019OmniMVS: End-to-End Learning for Omnidirectional Stereo Matchingcited by 21
  20. 2021Deep Learning for Multi-View Stereo via Plane Sweep: A Surveycited by 16
  21. 2020360^circ Depth Estimation from Multiple Fisheye Images with Origami Crown Representation of Icosahedroncited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 2; 2026: 4.

8 papers.

  1. 2024Depth Anywhere: Enhancing 360 Monocular Depth Estimation via Perspective Distillation and Unlabeled Data Augmentationcited by 38
  2. 2025AnyCalib: On-Manifold Learning for Model-Agnostic Single-View Camera Calibrationcited by 17
  3. 2025Extending Foundational Monocular Depth Estimators to Fisheye Cameras with Calibration Tokenscited by 9
  4. 2026Fisheye3R: Adapting Unified 3D Feed-Forward Foundation Models to Fisheye Lensescited by 4
  5. 2024nvTorchCam: An Open-source Library for Camera-Agnostic Differentiable Geometric Visioncited by 1
  6. 2026VisTa3D: A Dataset and Benchmark for Thin Object Reconstruction from Vision, Tactile, and 3D Point Cloudscited by 1
  7. 2026DepthMaster: Unified Monocular Depth Estimation for Perspective and Panoramic Imagescited by 0
  8. 2026From Perspective to Fisheye Depth Estimation and Open-Vocabulary Segmentationcited by 0