We will focus on how to do depth estimation using deep learning and traditional stereo matching methods.
1.FlowNet：Learning Optical Flow with Convolutional Networks(ICCV2015)
2.Computing the Stereo Matching Cost with a Convolutional Neural Network(cvpr2015)
1.DispNet:A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimatimation(cvpr2016)
2.Deep stereo fusion： combining multiple disparity hypotheses with deep-learning(3DV2016)
3.Efficient Deep Learning for Stereo Matching(cvpr2016)
1.GCNet:End-to-end learning of geometry and context for deep stereo regression(iccv2017)
2.Self-Supervised Learning for Stereo Matching with Self-Improving Ability(arxiv2017)
3.Unsupervised Learning of Stereo Matching(ICCV2017)
4.End-to-End Training of Hybrid CNN-CRF Models for Stereo(CVPR2017)
5.FlowNet 2.0： Evolution of Optical Flow Estimation with Deep Networks(CVPR2017)
6.Monodepth：Unsupervised Monocular Depth Estimation with Left-Right Consistency(cvpr2017)
1.Deep Material-aware Cross-spectral Stereo Matching(cvpr2018)
2.Deep Stereo Matching with Explicit Cost Aggregation Sub-Architecture(AAAI2018)
3.Deep Virtual Stereo Odometry:Leveraging Deep Depth Prediction for Monocular Direct Sparse Odometry(ECCV2018)
4.DenseMepNet：Fast Disparity Estimation using Dense Networks(ICRA2018)
5.Deep Ordinal Regression Network for Monocular Depth Estimation(cvpr2018)
6.Learning for Disparity Estimation through Feature Constancy(cvpr2018)
7.Left-Right Comparative Recurrent Model for Stereo Matching(CVPR2018)
8.MSFNet:End-to-End Learning of Multi-scale Convolutional Neural Network for Stereo Matching(ACML2018)
9.MVSNet:Depth Inference for Unstructured Multi-view Stereo(Eccv2018)
10.Practical Deep Stereo (PDS):Toward applications-friendly deep stereo matching(2018)
11.T2Net:Synthetic-to-Realistic Translation for Solving Single-Image Depth Estimation Tasks(ECCV2018)
12.Multi-scale CNN stereo and pattern removal technique for underwater active stereo system(3DV2018)
13.ASN-ActiveStereoNet End-to-End Self-Supervised Learning for Active Stereo Systems(ECCV2018)
14.Sparse_Cost_Volume_for_Efficient_Stereo_Matching(2018)
15.StereoNet:Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Prediction(ECCV2018)
16.Pyramid Stereo Matching Network(cvpr2018)
17.Zoom and Learn： Generalizing Deep Stereo Matching to Novel Domains(cvpr2018)
18.Megadepth: Learning single-view depth prediction from internet photos(CVPR2018)
19.Look Deeper into Depth: Monocular Depth Estimation with Semantic Booster and Attention-Driven Loss(ECCV2018)
1.360SD-Net：360° Stereo Depth Estimation with Learnable Cost Volume(iccvw2019)
2.AnyNet：Anytime Stereo Image Depth Estimation on Mobile Devices(ICRA2019)
3.CNN-based Cost Volume Analysis as Confidence Measure for Dense Matching(ICCVW2019)
4.CSPN：Learning Depth with Convolutional Spatial Propagation Network(2019)
5.DeepPruner： Learning Efficient Stereo Matching via Differentiable PatchMatch(ICCV2019)
6.DSMNet：Domain-invariant Stereo Matching Networks(2019)
7.FD-Fusion：Fast Stereo Disparity Maps Refinement By Fusion of Data-Based And Model-Based Estimations(3DV2019)
8.GA-Net：Guided Aggregation Net for End-to-end Stereo Matching(CVPR2019)
9.GSM：Guided Stereo Matching(cvpr2019)
10.GwcNet：Group-wise Correlation Stereo Network(cvpr2019)
11.HD3Stereo:Hierarchical Discrete Distribution Decomposition for Match Density Estimation(cvpr2019)
12.Shift Convolution Network for Stereo Matching(arxiv2019)
13.HSM：Hierarchical Deep Stereo Matching on High-resolution Images(cvpr2019)
14.ISGMR：Fast and Differentiable Message Passing for Stereo Vision(2019)
15.Learn Stereo, Infer Mono：Siamese Networks for Self-Supervised, Monocular, Depth Estimation(cvprw2019)
16.MADNet：Real-Time Self-Adaptive Deep Stereo(cvpr2019oral)
17.Monodepth2：Digging Into Self-Supervised Monocular Depth Estimation(iccv2019)
18.Multi-scale Cross-form Pyramid Network for Stereo Matching(ICIEA2019)
19.MVS：Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference(cvpr2019)
20.Region Deformer Networks for Unsupervised Depth Estimation from Unconstrained Monocular Videos(IJCAI2019)
21.SENSE：a Shared Encoder Network for Scene-flow Estimation(Iccv2019oral)
22.struct2depth：Depth Prediction Without the Sensors Leveraging Structure for Unsupervised Learning from Monocular Videos(AAAI2019)
23.TW-SMNet：Deep Multitask Learning of Tele-Wide Stereo Matching
24.Unsupervised Monocular Depth and Ego-motion Learning with Structure and Semantics(cvprw2019)
25.unsupervised monocular depth eatimation with clear boundaries(ICLR2019)
26.Neural rgb (r) d sensing： Depth and uncertainty from a video camera(cvpr2019oral)
27.Generating and Exploiting Probabilistic Monocular Depth Estimates(2019)
28.Learning Dense Wide Baseline Stereo Matching for People(ICCVW2019)
29.Depth from Videos in the Wild： Unsupervised Monocular Depth Learning from Unknown Cameras(ICCV2019)
30.Learning Single Camera Depth Estimation using Dual-Pixels(ICCV2019oral)
31.Single-Image Depth Inference Using Generative Adversarial Networks(sensors2019)
32.Structured Coupled Generative Adversarial Networks for Unsupervised Monocular Depth Estimation(2019)
33.EdgeStereo： An Effective Multi-Task Learning Network for Stereo Matching and Edge Detection(2019)
34.AMNet:Deep Atrous Multiscale Stereo Disparity Estimation Networks(2019)
35.Learning to Adapt for Stereo(cvpr2019)
36.Unsupervised Cross-Spectral Stereo Matching by Learning to Synthesize(AAAI2019)
37.Semantic Stereo Matching with Pyramid Cost Volumes(ICCV2019)
38.SuperDepth: Self-Supervised, Super-Resolved Monocular Depth Estimation(https://arxiv.org/pdf/1810.01849.pdf)
39.DSNet： Joint Learning for Scene Segmentation and Disparity Estimation(ICRA2019)
40.Mannequin：Learning the Depths of Moving People by Watching Frozen People(CVPR2019)
41. UnOS： Unified Unsupervised Optical-flow and Stereo-depth Estimation by Watching Videos(cvpr2019)
42. Depth Estimation and Semantic Segmentation from a Single RGB Image Using a Hybrid Convolutional Neural Network(sensors2019)
43. Refine and Distill: Exploiting Cycle-Inconsistency and Knowledge Distillation for Unsupervised Monocular Depth Estimation(cvpr2019)
44. Depth from a polarisation + RGB stereo pair(CVPR2019)
45. Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimation(CVPR2019)
46. Learning monocular depth estimation infusing traditional stereo knowledge(cvpr2019)
47. Student Becoming the Master: Knowledge Amalgamation for Joint Scene Parsing, Depth Estimation, and More(CVPR2019)
48. Bridging Stereo Matching and Optical Flow via Spatiotemporal Correspondence(CVPR2019)
49. Multi-Level Context Ultra-Aggregation for Stereo Matching(CVPR2019)
50. Autodispnet: Improving disparity estimation with automl(ICCV2019)
1.AcfNet：Adaptive Unimodal Cost Volume Filtering for Deep Stereo Matching(AAAI2020)
2.Du2Net： Learning Depth Estimation from Dual-Cameras and Dual-Pixels
3.FADNet：A Fast and Accurate Network for Disparity Estimation（ICRA2020）
4.Fast_DS：Fast Deep Stereo with 2D Convolutional Processing of Cost Signatures(WACV2020)
5.LFattNet：Attention-based View Selection Networks for Light-field Disparity Estimation(AAAI2020)
6.CasMVSNet：Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching(cvpr2020oral)
7.Fast-MVSNet：Sparse-to-Dense Multi-View Stereo With Learned Propagation and Gauss-Newton Refinement(cvpr2020)
8.Real-Time Semantic Stereo Matching(ICRA2020)
9.Self-supervised Monocular Trained Depth Estimation using Self-attention and Discrete Disparity Volume
10.Uncertainty Estimation for End-To-End Learned Dense Stereo Matching via Probabilistic Deep Learning
11.3D Packing for Self-Supervised Monocular Depth Estimation(2020cvproral)
12.MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask(cvpr2020oral)
13.A Survey on Deep Learning Techniques for Stereo-based Depth Estimation(arxiv2020)
14.Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidance(ECCV2020)
15. Self-supervised Object Motion and Depth Estimation from Video(CVPRW2020)
16. Improving Deep Stereo Network Generalization with Geometric Priors(arxiv2020-nvidia)
17. What Matters in Unsupervised Optical Flow(ECCV2020oral)
18. DeepSFM: Structure From Motion Via Deep Bundle Adjustment(ECCV2020)
19. Calibrating Self-supervised Monocular Depth Estimation(arxiv2020)
20. Cascade Network for Self-Supervised Monocular Depth Estimation(arxiv2020)
21. PRAFlow RVC: Pyramid Recurrent All-Pairs Field Transforms for Optical Flow Estimation in Robust Vision Challenge 2020
22. DESC：Domain Adaptation for Depth Estimation via Semantic Consistency(BMVC2020oral)
23. Improving Monocular Depth Estimation by Leveraging Structural Awareness and Complementary Datasets(ECCV2020 Y-tech)
24. CNN-Based Simultaneous Dehazing and Depth Estimation(ICRA2020)
25. Pseudo RGB-D for Self-Improving Monocular SLAM and Depth Prediction
26. Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidance(ECCV2020)
27. Consistent Video Depth Estimation(SIGGRAPH 2020)
28. MiDaS-v2：Towards Robust Monocular Depth Estimation Mixing Datasets for Zero-Shot Cross-Dataset Transfer(TPAMI2020)
29. Flow2Stereo： Effective Self-Supervised Learning of Optical Flow and Stereo Matching(CVPR2020)
30. BiFuse: Monocular 360◦ Depth Estimation via Bi-Projection Fusion(CVPR2020)
31. Focus on defocus: bridging the synthetic to real domain gap for depth estimation(CVPR2020)
32. Bi3D: Stereo Depth Estimation via Binary Classifications(CVPR2020)
33. Towards Better Generalization: Joint Depth-Pose Learning without PoseNet(CVPR2020)
34. Domain Decluttering: Simplifying Images to Mitigate Synthetic-Real Domain Shift and Improve Depth Estimation(CVPR2020)
35. Stereopagnosia: Fooling Stereo Networks with Adversarial Perturbations(arxiv2020)
36. NLCA-Net a non-local context attention network for stereo matching(ATSIPA2020)
37. Adaptive confidence thresholding for semi-supervised monocular depth estimation(arxiv2020)
38. Domain-invariant Stereo Matching Networks(ECCV2020)
39. Matching-space Stereo Networks for Cross-domain Generalization(3DV2020)
40. Hierarchical Neural Architecture Search for Deep Stereo Matching(NIPs2020)
41. EDNet: Improved DispNet for Efficient Disparity Estimation(arxiv2020)
42. Monocular Depth Estimation via Listwise Ranking using the Plackett-Luce Model(arxiv2020)
43. Geometry-based Occlusion-Aware Unsupervised Stereo Matching for Autonomous Driving(arxiv2020)
44. Relative Depth Estimation as a Ranking Problem(SIU2020)
45. Neural Ray Surfaces for Self-Supervised Learning of Depth and Ego-motion(arxiv2020)
46. Learning Monocular Dense Depth from Events(3DV2020)
47. MobileDepth: Efficient Monocular Depth Prediction on Mobile Devices(arxiv2020)
48. Polka Lines：Learning Structured Illumination and Reconstruction for Active Stereo（arxiv2020）
- Symmetric Stereo Matching for Occlusion Handling(cvpr2005)
- Robust stereo matching with improved graph and surface models and occlusion handling(JVCI2010)
- A Fast Dense Stereo Matching Algorithm with an Application to 3D Occupancy Mapping using Quadrocopters(ICRA2015)
- Determining occlusions from space and time image reconstructions(cvpr2016)
- Occlusion and Error Detection for Stereo Matching and Hole Filling Using Dynamic Programming(sist2016)
- Determining occlusions from space and time image reconstructions(ICIP2017)
- Feature_Ensemble_Network_with_Occlusion Disambiguation for Accurate Patch-Based Stereo Matching(TIS2017)
- Hide-and-Seek： Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localization(ICCV2017)
- Occlusion Aware Unsupervised Learning of Optical Flow(cvpr2018)
- Occlusions, motion and depth boundaries with a generic network for disparity, optical flow or scene flow estimation(ECCV2018)
- One-view occlusion detection for stereo matching with a fully connected CRF model (TIP2019)
- PWOC-3D：Deep Occlusion-Aware End-to-End Scene Flow Estimation(arxiv2019)
- Segment-Based Disparity Refinement With Occlusion Handling for Stereo Matching(TIP2019)
- SelFlow： Self-Supervised Learning of Optical Flow(cvpr2019)
- StereoDRNet： Dilated Residual StereoNet(cvpr2019)
Stereo Processing by Semiglobal Matching and Mutual Information(TPAMI2008)
GPU optimization for the SGM stereo algorithms(ICCP2010)
REAL-TIME DENSE STEREO MAPPING FOR MULTI-SENSOR NAVIGATION (2010)
Real-Time Stereo Vision System using Semi-Global Matching Disparity Estimation：Architecture and FPGA-Implementation(2010)
Semi-Global Matching – Motivation, Developments and Applications (2011)
Large Scale Semi-Global Matching on the CPU(2014)
Embedded real-time stereo estimation via Semi-Global Matching on the GPU(iccs2016)
GPU-Accelerated Real-Time Stereo Matching(2017)
SGM-Nets： Semi-global matching with neural networks(CVPR2017)
GPU-enhanced Multimodal Dense Matching(2018)
Real-time CUDA-based stereo matching using cyclops2 algorithms(2018)
FD_cudaSGM：Fast Stereo Disparity Maps Refinement By Fusion of Data-Based And Model-Based Estimations(3DV2019)
QUANTITATIVE COMPARISON BETWEEN NEURAL NETWORK- AND SGM-BASED STEREO MATCHING(2019)
Half Resolution Semi-Global Stereo Matching
MISGM-GPU：Mutual Information based Semi-Global Stereo Matching on the GPU
Real-Time Semi-Global Matching Using CUDA Implementation
Real-Time Stereo Vision using Semi-Global Matching on Programmable Graphics Hardware