awesome-depth

A curated list of publication for depth estimation

0. Survey

[1] Dijk et al, How do neural networks see depth in single images? PDF

[2] Amlaan et al, Monocluar depth estimation: A survey, PDF

[3] Zhao et al, Monocular Depth Estimation Based On Deep Learning: An Overview, PDF

1. Monocular Depth (Fully Supervised)

[1] Eigen et al, Depth Map Prediction from a Single Image using a Multi-Scale Deep Network, NIPS 2014, Web

[2] Eigen et al, Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture, ICCV 2015, Web

[3] Laina et al, Deeper Depth Prediction with Fully Convolutional Residual Networks, 3DV 2016, Code

[4] Chen et al, Single-Image Depth Perception in the Wild, NIPS 2016, Web

[5] Li et al, A Two-Streamed Network for Estimating Fine-Scaled Depth Maps from Single RGB Images, ICCV 2017, PDF

[6] Xu et al, Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation, CVPR 2018, PDF

[7] Xu et al, PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network, CVPR 2018, PDF

[8] Qi et al, GeoNet: Geometric Neural Network for Joint Depth and Surface Normal Estimation, CVPR 2018, PDF

[9] Fu et al, Deep Ordinal Regression Network for Monocular Depth Estimation, CVPR 2018, PDF

[10] Zhang et al, Joint Task-Recursive Learning for Semantic Segmentation and Depth Estimation, ECCV 2018, PDF

[11] Jiao et al, Look Deeper into Depth: Monocular Depth Estimation with Semantic Booster and Attention-Driven Loss, ECCV 2018, PDF

[12] Cheng et al, Depth Esimation via Affinity Learning with Convolutional Spatial Propagation Network, ECCV 2018, PDF, Code

[13] Lee et al, Monocular depth estimation using relative depth maps, CVPR 2019, PDF, Code

[14] Lee et al, From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation, Arxiv, PDF, Code

[15] Zhang et al, Pattern-Affinitive Propagation across Depth, Surface Normal and Semantic Segmentation, CVPR 2019, PDF

[16] Zhang et al, Exploiting temporal consistency for real-time video depth estimation, ICCV 2019, PDF, Code

2. Monocular Depth (Semi- / Un-Supervised)

2.1 Stereo Consistency

[1] Garg et al, Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue, ECCV 2016, Code

[2] Godard et al, Unsupervised Monocular Depth Estimation with Left-Right Consistency, CVPR 2017, Web

[3] Kuznietsov et al, Semi-Supervised Deep Learning for Monocular Depth Map Prediction, CVPR 2017, Code

[4] Luo et al, Single View Stereo Matching, CVPR 2018, Code

[5] Godard et al, Digging Into Self-Supervised Monocular Depth Estimation, aXiv 2018, PDF

[6] Lai et al, Bridging Stereo Matching and Optical Flow via Spatio temporal, CVPR 2019, PDF, Code

[7] Tosi et al, Learning monocular depth estimation infusing traditional stereo knowledge, CVPR 2019, PDF Code

[8] Garg et al, Learning Single Camera Depth Estimation using Dual-Pixels, ICCV 2019, PDF Code

[9] Zhang et al, Du2Net: Learning Depth Estimation from Dual-Cameras and Dual-Pixels, arXiv 2020, PDF

2.2 Multi View

[1] Zhou et al, Unsupervised Learning of Depth and Ego-Motion from Video, CVPR 2017, Web

[2] Im et al, Robust Depth Estimation from Auto Bracketed Images, CVPR 2018, PDF

[3] Yin et al, GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose, CVPR 2018,Code

[4] Wang et al, Learning Depth from Monocular Videos using Direct Methods, CVPR 2018, Code

[5] Yang et al, LEGO: Learning Edge with Geometry all at Once by Watching Videos, CVPR 2018, Code

[6] Mahjourian et al, Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraints, CVPR 2018, PDF

[7] Zhan et al, Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction, CVPR 2018, Web

[8] Ran et al, Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation, CVPR 2019, PDF, Code

[9] Bian et al, Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video, NIPS 2019, PDF, Code

[10] Luo et al, Consistent Video Depth Estimation, SIGGRAPH 2020, Web

[11] Teed et al, DEEPV2D: VIDEO TO DEPTH WITH DIFFERENTIABLE STRUCTURE FROM MOTION, ICLR 2020, PDF Code

[12] Guizilini et al, 3D Packing for Self-Supervised Monocular Depth Estimation, CVPR 2020, PDF Code

[13] Zhao et al, Towards Better Generalization: Joint Depth-Pose Learning without PoseNet, CVPR 2020 PDF Code

[14] Bian et al, Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video, NeurIPs 2019 PDF Code

3. Depth Completion/Super-resolution

[1] Cheng et al, Learning Depth with Convolutional Spatial Propagation Network, arXiv 2018, PDF, Code

[2] Zhang et al, Deep Depth Completion of a Single RGB-D Image, CVPR 2018, PDF

[3] Qiu et al, DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color Image, CVPR 2019, PDF, Code

[4] Chen et al, Learning Joint 2D-3D Representations for Depth Completion, ICCV 2019, PDF

[5] Tang et al, Learning Guided Convolutional Network for Depth Completion, arXiv 2019, PDF, Code

4. Depth Fusion

[1] Marin et al, Reliable Fusion of ToF and Stereo Depth Driven by Confidence Measures, ECCV 2016, PDF

[2] Agresti et al, Deep Learning for Confidence Information in Stereo and ToF Data Fusion, ICCVW 2017, Web

5. Depth Dataset

[1] Srinivasan et al, Aperture Supervision for Monocular Depth Estimation, CVPR 2018, Code

[2] Li et al, MegaDepth: Learning Single-View Depth Prediction from Internet Photos, CVPR 2018, Web

[3] Monocular Relative Depth Perception with Web Stereo Data Supervision, CVPR 2018, PDF

[4] Li et al, Learning the depths of moving people by watching frozen people, CVPR 2019, Web

[5] Chen et al, Learning Single-Image Depth from Videos using Quality Assessment Networks, CVPR 2019, PDF

[6] Li et al, Learning the Depths of Moving People by Watching Frozen People, CVPR 2019(oral), PDF

[7] See Link for more conventional data sets.

6. 3D Photography

[1] Zhou et al, Stereo Magnification: Learning view synthesis using multiplane images, SIGGRAPH 2018, Web

[2] Niklaus et al, 3D Ken Burns Effect from a Single Image, SIGGRAPH 2019, PDF Code

[3] Wiles et al, SynSin: End-to-end View Synthesis from a Single Image, CVPR 2020, Web

[4] Shih et al, 3D Photography using Context-aware Layered Depth Inpainting, CVPR 2020, Web

[5] Mildenhall et al, Representing Scenes as Neural Radiance Fields for View Synthesis, arXiv 2020, Web

[6] Chen et al, Monocular Neural Image Based Rendering with Continuous View Control, ICCV 2019, Web

[7] Chen et al, Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction, AAAI 2018, PDF

[8] Kopf et al, One Shot 3D Photography, SIGGRAPH 2020 PDF Web

7. RGB-D Application

8. Optical Flow & Scene Flow

[1] Dosovitskiy et al, FlowNet: Learning optical flow with convolutional networks, CVPR 2015, PDF

[2] Yu et al, Back to basics: Unsupervised learning of optical flow via brightness constancy and motion smoothness, ECCV 2016 Workshop, PDF

[3] Bailer et al, CNN-based Patch Matching for Optical Flow with Thresholded Hinge Embedding Loss, CVPR 2017, PDF

[4] Ranjan et al, Optical Flow Estimation using a Spatial Pyramid Network(SpyNet), CVPR 2017, Code

[5] Ilg et al, FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks, CVPR 2017, Code

[6] Sun et al, PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume, CVPR 2018, Code

[7] Wang et al, Occlusion Aware Unsupervised Learning of Optical Flow, CVPR 2018, PDF

[6] Hui et al, LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation, CVPR 2018, PDF