mlsanityData to 7 Oct 2026

Full Surround Monodepth from Multiple Cameras

arXiv 2104.00152 ↗First posted 31 Mar 2021cs.CVcited by 41

Not on the map. Why?

Abstract (arXiv)

Self-supervised monocular depth and ego-motion estimation is a promising approach to replace or supplement expensive depth sensors such as LiDAR for robotics applications like autonomous driving. However, most research in this area focuses on a single monocular camera or stereo pairs that cover only a fraction of the scene around the vehicle. In this work, we extend monocular self-supervised depth and ego-motion estimation to large-baseline multi-camera rigs. Using generalized spatio-temporal contexts, pose consistency constraints, and carefully designed photometric loss masking, we learn a single network generating dense, consistent, and scale-aware point clouds that cover the same full surround 360 degree field of view as a typical LiDAR scanner. We also propose a new scale-consistent evaluation metric more suitable to multi-camera settings. Experiments on two challenging benchmarks illustrate the benefits of our approach over strong baselines.

Key facts. Cited by 41 papers in the map (data through 7 Oct 2026). Builds on 34 of its 54 references that are in the map. First posted on arXiv 31 Mar 2021.

Builds on

34 of 54 references.

References · 34

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  3. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  4. 2018Group Normalizationcited by 1,514
  5. 2015Spatial Transformer Networkscited by 1,423
  6. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  7. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
  8. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
  9. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
  10. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
  11. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 455
  12. 20193D Packing for Self-Supervised Monocular Depth Estimationcited by 437
22 more
  1. 2016Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescuecited by 368
  2. 2017End-to-End Learning of Geometry and Context for Deep Stereo Regressioncited by 359
  3. 2018DeepMVS: Learning Multi-view Stereopsiscited by 277
  4. 2019Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Videocited by 244
  5. 2017Geometric Loss Functions for Camera Pose Regression with Deep Learningcited by 224
  6. 2017Learning a Multi-View Stereo Machinecited by 194
  7. 2018Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraintscited by 179
  8. 2019Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Camerascited by 170
  9. 2018Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstructioncited by 159
  10. 2015Stereo Matching by Training a Convolutional Neural Network to Compare Image Patchescited by 151
  11. 2020Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidancecited by 148
  12. 2019DPSNet: End-to-end Deep Plane Sweep Stereocited by 115
  13. 2017Semi-Supervised Deep Learning for Monocular Depth Map Predictioncited by 109
  14. 2017UnDeepVO: Monocular Visual Odometry through Unsupervised Deep Learningcited by 95
  15. 2018SuperDepth: Self-Supervised, Super-Resolved Monocular Depth Estimationcited by 64
  16. 2020MatryODShka: Real-time 6DoF Video View Synthesis using Multi-Sphere Imagescited by 64
  17. 2019Learning Unsupervised Multi-View Stereopsis via Robust Photometric Consistencycited by 40
  18. 2019360SD-Net: 360deg Stereo Depth Estimation with Learnable Cost Volumecited by 40
  19. 2019OmniMVS: End-to-End Learning for Omnidirectional Stereo Matchingcited by 21
  20. 2020Neural Ray Surfaces for Self-Supervised Learning of Depth and Ego-motioncited by 20
  21. 2020Distortion-aware Monocular Depth Estimation for Omnidirectional Imagescited by 17
  22. 2018Unsupervised Learning of Monocular Depth Estimation with Bundle Adjustment, Super-Resolution and Clip Losscited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 7; 2023: 14; 2024: 12; 2025: 5; 2026: 3.

41 papers.

Sort:

By area:

  1. 2023Tri-Perspective View for Vision-Based 3D Semantic Occupancy Predictioncited by 404
  2. 2023SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Drivingcited by 310
  3. 2023SelfOcc: Self-Supervised Vision-Based 3D Occupancy Predictioncited by 133
  4. 2022SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimationcited by 76
  5. 2023Robust Monocular Depth Estimation under Challenging Conditionscited by 58
  6. 2024DrivingForward: Feed-forward 3D Gaussian Splatting for Driving Scene Reconstruction from Flexible Surround-view Inputcited by 53
  7. 2023R3D3: Dense 3D Reconstruction of Dynamic Scenes from Multiple Camerascited by 39
  8. 2023OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environmentscited by 39
  9. 2022TiG-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry Learningcited by 37
  10. 2024OccFusion: Multi-Sensor Fusion Framework for 3D Semantic Occupancy Predictioncited by 32
  11. 2022Learning Optical Flow, Depth, and Scene Flow without Real-World Labelscited by 31
  12. 2024RSA: Resolving Scale Ambiguities in Monocular Depth Estimators through Language Descriptionscited by 20
29 more
  1. 2022Multi-Camera Collaborative Depth Prediction via Consistent Structure Estimationcited by 16
  2. 2023EGA-Depth: Efficient Guided Attention for Self-Supervised Multi-Camera Depth Estimationcited by 16
  3. 2024InverseMatrixVT3D: An Efficient Projection Matrix-Based Approach for 3D Occupancy Predictioncited by 14
  4. 2024HybridOcc: NeRF Enhanced Transformer-based Multi-Camera 3D Occupancy Predictioncited by 12
  5. 2022SfM-TTR: Using Structure from Motion for Test-Time Refinement of Single-View Depth Networkscited by 10
  6. 2024M2Depth: Self-supervised Two-Frame Multi-camera Metric Depth Estimationcited by 10
  7. 2022Mind The Edge: Refining Depth Edges in Sparsely-Supervised Monocular Depth Estimationcited by 8
  8. 2023Diffusion-Augmented Depth Prediction with Sparse Annotationscited by 8
  9. 2024Towards Cross-View-Consistent Self-Supervised Surround Depth Estimationcited by 7
  10. 2023Adjacent-view Transformers for Supervised Surround-view Depth Estimationcited by 6
  11. 2023DeLiRa: Self-Supervised Depth, Light, and Radiance Fieldscited by 5
  12. 2024SDGE: Stereo Guided Depth Estimation for 360^circ Camera Setscited by 5
  13. 2024Towards Scale-Aware Full Surround Monodepth with Transformerscited by 5
  14. 2022BEV-LGKD: A Unified LiDAR-Guided Knowledge Distillation Framework for BEV 3D Object Detectioncited by 4
  15. 2023A Simple Framework for 3D Occupancy Estimation in Autonomous Drivingcited by 4
  16. 2023Robust Self-Supervised Extrinsic Self-Calibrationcited by 4
  17. 2024Unveiling the Depths: A Multi-Modal Fusion Framework for Challenging Scenarioscited by 4
  18. 2024TiGDistill-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry Learning Distillationcited by 4
  19. 2023BEVScope: Enhancing Self-Supervised Depth Estimation Leveraging Bird's-Eye-View in Dynamic Scenarioscited by 3
  20. 2023FSNet: Redesign Self-Supervised MonoDepth for Full-Scale Depth Prediction for Autonomous Drivingcited by 2
  21. 2025sshELF: Single-Shot Hierarchical Extrapolation of Latent Features for 3D Reconstruction from Sparse-Viewscited by 1
  22. 2025Semi-SMD: Semi-Supervised Metric Depth Estimation via Surrounding Cameras for Autonomous Drivingcited by 1
  23. 2025PFDepth: Heterogeneous Pinhole-Fisheye Joint Depth Estimation via Distortion-aware Gaussian-Splatted Volumetric Fusioncited by 1
  24. 2024The ADUULM-360 Dataset -- A Multi-Modal Dataset for Depth Estimation in Adverse Weathercited by 0
  25. 2025Intrinsic Image Decomposition for Robust Self-supervised Monocular Depth Estimation on Reflective Surfacescited by 0
  26. 2025Scale-invariant and View-relational Representation Learning for Full Surround Monocular Depthcited by 0
  27. 2026GeoSurDepth: Harnessing Foundation Model for Spatial Geometry Consistency-Oriented Self-Supervised Surround-View Depth Estimationcited by 0
  28. 2026Cross-Vehicle 3D Geometric Consistency for Self-Supervised Surround Depth Estimation on Articulated Vehiclescited by 0
  29. 2026CascadeOcc: Rethinking 3D Occupancy World Models with Cascaded VQ Representationscited by 0