Monocular Depth Estimation: A Survey
Not on the map. Why?
Abstract (arXiv)
Monocular depth estimation is often described as an ill-posed and inherently ambiguous problem. Estimating depth from 2D images is a crucial step in scene reconstruction, 3Dobject recognition, segmentation, and detection. The problem can be framed as: given a single RGB image as input, predict a dense depth map for each pixel. This problem is worsened by the fact that most scenes have large texture and structural variations, object occlusions, and rich geometric detailing. All these factors contribute to difficulty in accurate depth estimation. In this paper, we review five papers that attempt to solve the depth estimation problem with various techniques including supervised, weakly-supervised, and unsupervised learning techniques. We then compare these papers and understand the improvements made over one another. Finally, we explore potential improvements that can aid to better solve this problem.
Key facts. Cited by 37 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Jan 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 8; 2022: 6; 2023: 6; 2024: 7; 2025: 9; 2026: 1.
37 papers.
Sort:
By area:
- 2022Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentationcited by 152
- 2022PanoFormer: Panorama Transformer for Indoor 360 Depth Estimationcited by 94
- 2023Booster: a Benchmark for Depth from Images of Specular and Transparent Surfacescited by 33
- 2023DaRF: Boosting Radiance Fields from Sparse Inputs with Monocular Depth Adaptationcited by 25
- 2021Beyond Image to Depth: Improving Depth Prediction using Echoescited by 24
- 2024Deep Learning-based Depth Estimation Methods from Monocular Image and Videos: A Comprehensive Surveycited by 15
- 2022ChiTransformer:Towards Reliable Stereo from Cuescited by 14
- 20243D Scene Geometry Estimation from 360^circ Imagery: A Surveycited by 11
- 2024Self-Evolving Depth-Supervised 3D Gaussian Splatting from Rendered Stereo Pairscited by 11
- 2025Depth Anything at Any Conditioncited by 11
- 2023PanopticNeRF-360: Panoramic 3D-to-2D Label Transfer in Urban Scenescited by 9
- 2021Real-Time Monocular Human Depth Estimation and Segmentation on Embedded Systemscited by 4
25 more
- 2021Traffic-Net: 3D Traffic Monitoring Using a Single Cameracited by 4
- 2021Detecting and Identifying Optical Signal Attacks on Autonomous Driving Systemscited by 4
- 2024Amodal Depth Anything: Amodal Depth Estimation in the Wildcited by 4
- 2022Sensor Data Validation and Driving Safety in Autonomous Driving Systemscited by 3
- 2025Approximate Supervised Object Distance Estimation on Unmanned Surface Vehiclescited by 3
- 2025Niagara: Normal-Integrated Geometric Affine Field for Scene Reconstruction from a Single Viewcited by 3
- 2021Marine vessel tracking using a monocular cameracited by 2
- 2022Unsupervised Single-shot Depth Estimation using Perceptual Reconstructioncited by 2
- 2023ADU-Depth: Attention-based Distillation with Uncertainty Modeling for Depth Estimationcited by 2
- 2023Leveraging a realistic synthetic database to learn Shape-from-Shading for estimating the colon depth in colonoscopy imagescited by 2
- 2022Monocular Spherical Depth Estimation with Explicitly Connected Weak Layout Cuescited by 1
- 2023RGB-D-Fusion: Image Conditioned Depth Diffusion of Humanoid Subjectscited by 1
- 2024Learning Monocular Depth from Focus with Event Focal Stackcited by 1
- 2024Human Insights Driven Latent Space for Different Driving Perspectives: A Unified Encoder for Efficient Multi-Task Inferencecited by 1
- 2025DB3D-L: Depth-aware BEV Feature Transformation for Accurate 3D Lane Detectioncited by 1
- 2025Endoscopic Depth Estimation Based on Deep Learning: A Surveycited by 1
- 2026SpiderCam: Low-Power Snapshot Depth from Differential Defocuscited by 1
- 2021Improved Point Transformation Methods For Self-Supervised Depth Predictioncited by 0
- 2021Progressive Depth Learning for Single Image Dehazingcited by 0
- 2021Unpaired Single-Image Depth Synthesis with cycle-consistent Wasserstein GANscited by 0
- 2024Mean of Means: A 10-dollar Solution for Human Localization with Calibration-free and Unconstrained Camera Settingscited by 0
- 2025Survey on Monocular Metric Depth Estimationcited by 0
- 2025Mean of Means: Human Localization with Calibration-free and Unconstrained Camera Settings (extended version)cited by 0
- 2025Enhancing Steering Estimation with Semantic-Aware GNNscited by 0
- 2025Projection-based Adversarial Attack using Physics-in-the-Loop Optimization for Monocular Depth Estimationcited by 0
- 2026SpiderCam: Low-Power Snapshot Depth from Differential Defocus18 Mar 2026
- 2025Projection-based Adversarial Attack using Physics-in-the-Loop Optimization for Monocular Depth Estimation31 Dec 2025
- 2025Endoscopic Depth Estimation Based on Deep Learning: A Survey28 Jul 2025
- 2025Depth Anything at Any Condition2 Jul 2025
- 2025DB3D-L: Depth-aware BEV Feature Transformation for Accurate 3D Lane Detection19 May 2025
- 2025Enhancing Steering Estimation with Semantic-Aware GNNs21 Mar 2025
- 2025Niagara: Normal-Integrated Geometric Affine Field for Scene Reconstruction from a Single View16 Mar 2025
- 2025Mean of Means: Human Localization with Calibration-free and Unconstrained Camera Settings (extended version)18 Feb 2025
- 2025Survey on Monocular Metric Depth Estimation21 Jan 2025
- 2025Approximate Supervised Object Distance Estimation on Unmanned Surface Vehicles9 Jan 2025
- 2024Amodal Depth Anything: Amodal Depth Estimation in the Wild3 Dec 2024
- 2024Human Insights Driven Latent Space for Different Driving Perspectives: A Unified Encoder for Efficient Multi-Task Inference16 Sep 2024
25 more
- 2024Self-Evolving Depth-Supervised 3D Gaussian Splatting from Rendered Stereo Pairs11 Sep 2024
- 2024Mean of Means: A 10-dollar Solution for Human Localization with Calibration-free and Unconstrained Camera Settings30 Jul 2024
- 2024Deep Learning-based Depth Estimation Methods from Monocular Image and Videos: A Comprehensive Survey28 Jun 2024
- 2024Learning Monocular Depth from Focus with Event Focal Stack11 May 2024
- 20243D Scene Geometry Estimation from 360^circ Imagery: A Survey17 Jan 2024
- 2023Leveraging a realistic synthetic database to learn Shape-from-Shading for estimating the colon depth in colonoscopy images8 Nov 2023
- 2023ADU-Depth: Attention-based Distillation with Uncertainty Modeling for Depth Estimation26 Sep 2023
- 2023PanopticNeRF-360: Panoramic 3D-to-2D Label Transfer in Urban Scenes19 Sep 2023
- 2023RGB-D-Fusion: Image Conditioned Depth Diffusion of Humanoid Subjects29 Jul 2023
- 2023DaRF: Boosting Radiance Fields from Sparse Inputs with Monocular Depth Adaptation30 May 2023
- 2023Booster: a Benchmark for Depth from Images of Specular and Transparent Surfaces19 Jan 2023
- 2022Monocular Spherical Depth Estimation with Explicitly Connected Weak Layout Cues22 Jun 2022
- 2022Sensor Data Validation and Driving Safety in Autonomous Driving Systems30 Mar 2022
- 2022Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentation29 Mar 2022
- 2022PanoFormer: Panorama Transformer for Indoor 360 Depth Estimation17 Mar 2022
- 2022ChiTransformer:Towards Reliable Stereo from Cues9 Mar 2022
- 2022Unsupervised Single-shot Depth Estimation using Perceptual Reconstruction28 Jan 2022
- 2021Detecting and Identifying Optical Signal Attacks on Autonomous Driving Systems20 Oct 2021
- 2021Traffic-Net: 3D Traffic Monitoring Using a Single Camera19 Sep 2021
- 2021Real-Time Monocular Human Depth Estimation and Segmentation on Embedded Systems24 Aug 2021
- 2021Marine vessel tracking using a monocular camera23 Aug 2021
- 2021Unpaired Single-Image Depth Synthesis with cycle-consistent Wasserstein GANs31 Mar 2021
- 2021Beyond Image to Depth: Improving Depth Prediction using Echoes15 Mar 2021
- 2021Progressive Depth Learning for Single Image Dehazing21 Feb 2021
- 2021Improved Point Transformation Methods For Self-Supervised Depth Prediction18 Feb 2021
- 2022Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentationcited by 152
- 2022PanoFormer: Panorama Transformer for Indoor 360 Depth Estimationcited by 94
- 2023Booster: a Benchmark for Depth from Images of Specular and Transparent Surfacescited by 33
- 2023DaRF: Boosting Radiance Fields from Sparse Inputs with Monocular Depth Adaptationcited by 25
- 2021Beyond Image to Depth: Improving Depth Prediction using Echoescited by 24
- 2024Deep Learning-based Depth Estimation Methods from Monocular Image and Videos: A Comprehensive Surveycited by 15
- 2022ChiTransformer:Towards Reliable Stereo from Cuescited by 14
- 20243D Scene Geometry Estimation from 360^circ Imagery: A Surveycited by 11
- 2024Self-Evolving Depth-Supervised 3D Gaussian Splatting from Rendered Stereo Pairscited by 11
- 2025Depth Anything at Any Conditioncited by 11
- 2023PanopticNeRF-360: Panoramic 3D-to-2D Label Transfer in Urban Scenescited by 9
- 2021Real-Time Monocular Human Depth Estimation and Segmentation on Embedded Systemscited by 4
12 most cited of 36 All 36 (JSON)
- 2026SpiderCam: Low-Power Snapshot Depth from Differential Defocus18 Mar 2026
- 2025Projection-based Adversarial Attack using Physics-in-the-Loop Optimization for Monocular Depth Estimation31 Dec 2025
- 2025Endoscopic Depth Estimation Based on Deep Learning: A Survey28 Jul 2025
- 2025Depth Anything at Any Condition2 Jul 2025
- 2025DB3D-L: Depth-aware BEV Feature Transformation for Accurate 3D Lane Detection19 May 2025
- 2025Enhancing Steering Estimation with Semantic-Aware GNNs21 Mar 2025
- 2025Niagara: Normal-Integrated Geometric Affine Field for Scene Reconstruction from a Single View16 Mar 2025
- 2025Mean of Means: Human Localization with Calibration-free and Unconstrained Camera Settings (extended version)18 Feb 2025
- 2025Survey on Monocular Metric Depth Estimation21 Jan 2025
- 2025Approximate Supervised Object Distance Estimation on Unmanned Surface Vehicles9 Jan 2025
- 2024Amodal Depth Anything: Amodal Depth Estimation in the Wild3 Dec 2024
- 2024Human Insights Driven Latent Space for Different Driving Perspectives: A Unified Encoder for Efficient Multi-Task Inference16 Sep 2024
12 newest of 36 All 36 (JSON)