For anyone who wants to do research about 3D monocular reconstruction.
If you find the awesome paper/code/dataset or have some suggestions, please feel free to contact linzhuochen@foxmail.com. Thanks for your valuable contribution to the research community π
Last update: 2022-04-12
- Recent papers (from 2017)
- Recent papers (from 2017)
Keywords
dep.
: depth estimation
pose.
: pose estimation β | β video.
: video
seq.
: sequence β | β uns.
: unsupervised
recon.
: reconstruction β | β oth.
: other
Statistics: π₯ code is available & stars >= 100 β|β β citation >= 50
2017
-
[NIPS] Learning a Multi-View Stereo Machine. [
seq.
recon.
] -
[CVPR] DeMoN: Depth and Motion Network for Learning Monocular Stereo. [tensorflow] [
dep.
pos.
seq.
] π₯ β -
[CVPR] Unsupervised Learning of Depth and Ego-Motion from Video. [tensorflow] [
dep.
pos.
seq.
video.
uns.
] π₯ β -
[ICCV] SurfaceNet: An End-to-end 3D Neural Network for Multiview Stereopsis. [theano] [
seq.
recon.
] π₯ β
2018
-
[CVPR] Deep Ordinal Regression Network for Monocular Depth Estimation. [pytorch] [
dep.
] π₯ β -
[CVPR] Monocular Relative Depth Perception with Web Stereo Data Supervision. [caffe] [
dep.
] π₯ β -
[CVPR] MegaDepth: Learning Single-View Depth Prediction from Internet Photos. [pytorch] [
dep.
] π₯ β -
[CVPR] Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation [caffe] [
dep.
] π₯ β -
[CVPR] DeepMVS: Learning Multi-view Stereopsis [pytorch] [
dep.
seq.
] π₯ β -
[ECCV] MVSNet: Depth Inference for Unstructured Multi-view Stereo [pytorch] [
dep.
seq.
] π₯ β -
[3DV] MVDepthNet: Real-time Multiview Depth Estimation Neural Network [pytorch] [
dep.
seq.
video.
] π₯ β -
[ECCV] DeepTAM: Deep Tracking and Mapping. [tensorflow] [
dep.
seq.
video.
pose.
] π₯ β -
[ECCV] LS-Net: Learning to Solve Nonlinear Least Squares for Monocular Stereo [
dep.
seq.
video.
pose.
] π₯ β -
[CVPR] Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction. [caffe] [
dep.
pos.
seq.
video.
uns.
] π₯ β -
[CVPR] Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraints. [tensorflow] [
dep.
pos.
seq.
video.
uns.
] π₯ β -
[ICRA] UnDeepVO: Monocular Visual Odometry through Unsupervised Deep Learning. [
dep.
pos.
seq.
video.
uns.
] -
[CVPR] GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose. [[tensorflow]https://github.com/yzcjtr/GeoNet)] [
dep.
pos.
seq.
video.
uns.
oth.
]
2019
-
[Arxiv] From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation. [pytorch+tensorflow] [
dep.
] π₯ β -
[CVPR]Learning Single-Image Depth from Videos using Quality Assessment Networks [pytorch] [
dep.
] π₯ β -
[WACV] Revisiting Single Image Depth Estimation-Toward Higher Resolution Maps with Accurate Object Boundaries. [pytorch] [
dep.
] π₯ β -
[ICCV] Enforcing geometric constraints of virtual normal for depth prediction. [pytorch] [
dep.
] π₯ β -
[ICCV] Visualization of Convolutional Neural Networks for Monocular Depth Estimation. [pytorch] [
dep.
] π₯ β -
[ICLR] DPSNet: End-to-end Deep Plane Sweep Stereo. [pytorch] [
dep.
seq.
] π₯ β -
[CVPR] Neural RGBβD Sensing: Depth and Uncertainty from a Video Camera. [pytorch] [
dep.
seq.
video.
] π₯ β -
[3DV] Web Stereo Video Supervision for Depth Prediction from Dynamic Scenes. [pytorch] [[
dep.
seq.
video.
] π₯ β -
[CVPR] Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference. [tensorflow] [[
dep.
seq.
recon.
] π₯ β -
[ICCV] Point-Based Multi-View Stereo Network. [pytorch] [[
dep.
seq.
recon.
] π₯ β -
[ICCV] P-MVSNet: Learning Patch-wise Matching Confidence Aggregation for Multi-view Stereo. [[
dep.
seq.
recon.
] -
[ICCV] MVSCRF: Learning Multi-view Stereo with Conditional Random Fields. [
dep.
seq.
recon.
] -
[ICLR] BA-Net: Dense Bundle Adjustment Network. [tensorflow] [
dep.
seq.
video.
pose.
] π₯ β -
[AAAI] Depth Prediction without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videos. [tensorflow] [
dep.
seq.
video.
pose.
uns.
] π₯ β -
[ICCV] Digging Into Self-Supervised Monocular Depth Estimation. [pytorch] [
dep.
seq.
video.
pose.
uns.
] π₯ β -
[ICCV] Unsupervised Collaborative Learning of Keyframe Detection and Visual Odometry Towards Monocular Deep SLAM. [
dep.
seq.
video.
pose.
uns.
] -
[ICCV] Self-supervised Learning with Geometric Constraints in Monocular Video Connecting Flow, Depth, and Camera. [
dep.
seq.
video.
pose.
uns.
oth.
] -
[ICCV] Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation. [pytorch][
dep.
seq.
video.
pose.
uns.
oth.
]
2020
-
[Arxiv] DiverseDepth: Affine-invariant Depth Prediction Using Diverse Data. [pytorch] [
dep.
] π₯ β -
[CVPR] Structure-Guided Ranking Loss for Single Image Depth Prediction [pytorch] [
dep.
] π₯ β -
[TPAMI] Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer[pytorch] [
dep.
] π₯ β -
[CVPR] Normal Assisted Stereo Depth Estimation[pytorch] [
dep.
seq.
] π₯ β -
[ECCV] Occlusion-Aware Depth Estimation with Adaptive Normal Constraints. [
dep.
seq.
video.
] -
[TOG] Consistent Video Depth Estimation. [
dep.
seq.
video.
] -
[AAAI] Learning Inverse Depth Regression for Multi-View Stereo with Correlation Cost Volume [code] [
dep.
seq.
recon.
] -
[CVPR] Cascade Cost Volume for High-Resolutoin Multi-View Stereo and Stereo Matching [pytorch] [
dep.
seq.
recon.
] -
[CVPR] Deep Stereo using Adaptive Thin Volume Representation with Uncertainty Awareness. [pytorch] [
dep.
seq.
recon.
] -
[CVPR] Cost Volume Pyramid Based Depth Inference for Multi-View Stereo. [pytorch] [
dep.
seq.
recon.
] -
[CVPR] Fast-MVSNet: Sparse-to-Dense Multi-View Stereo with Learned Propagation and Gauss-Newton Refinement. [pytorch] [
dep.
seq.
recon.
] -
[CVPR] Attention-Aware Multi-View Stereo. [
dep.
seq.
recon.
] -
[CVPR] A Novel Recurrent Encoder-Decoder Structure for Large-Scale Multi-view Stereo Reconstruction from An Open Aerial Dataset. [tensorflow] [
dep.
seq.
recon.
] -
[ECCV] Pyramid Multi-view Stereo Net with Self-adaptive View aggregation. [pytorch] [
dep.
seq.
recon.
] -
[ECCV] Dense Hybird Recurrent Multi-view Stereo Net with Dynamic Consistency Checking. [pytorch] [
dep.
seq.
recon.
] -
[BMVC] Visibility-aware Multi-view Stereo Network. [pytorch] [
dep.
seq.
recon.
] -
[ICLR] DeepV2D: Video to Depth with Differentiable Structure From Motion[tensorflow] [
dep.
seq.
video.
pose.
] π₯ β -
[CVPR] 3D Packing for Self-Supervised Monocular Depth Estimation [tensorflow] [
dep.
seq.
video.
pose.
uns.
] π₯ β -
[CVPR] D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry [tensorflow] [
dep.
seq.
video.
pose.
uns.
] π₯ β -
[ECCV] Learning Monocular Visual Odometry via Self-Supervised Long-Term Modeling. [
dep.
seq.
video.
pose.
uns.
]
2021
-
[AAAI] Patch-Wise Attention Network for Monocular Depth Estimation. [
dep.
] -
[TPAMI] Virtual Normal: Enforcing Geometric Constraints for Accurate and Robust Depth Prediction[pytorch] [
dep.
] π₯ β -
[CVPR] AdaBins: Depth Estimation Using Adaptive Bins [pytorch] [
dep.
] π₯ β -
[CVPR] Boosting Monocular Depth Estimation with Sparse Guided Points [pytorch] [
dep.
] π₯ β -
[CVPR] Learning to Recover 3D Scene Shape from a Single Image. [pytorch] [
dep.
recon.
] π₯ β -
[ICCV] Vision Transformers for Dense Prediction [pytorch] [
dep.
oth.
] π₯ β -
[CVPR] Robust Consistent Video Depth Estimation.[pytorch] [
dep.
seq.
video.
] π₯ β -
[CVPR] NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video. [pytorch] [
seq.
video.
recon.
] π₯ β -
[3DV] VoRTX: Volumetric 3D Reconstruction With Transformers for Voxelwise View Selection and Fusion. [pytorch] [
seq.
video.
recon.
] π₯ β -
[WACV]Long-range Attention Network for Multi-View Stereo. [
dep.
seq.
recon.
] -
[CVPR] PatchmatchNet: Learned Multi-View Patchmatch Stereo [pytorch] [
dep.
seq.
recon.
] π₯ β -
[ICCV] AA-RMVSNet: Adaptive Aggregation Recurrent Multi-view Stereo Network [pytorch] [
dep.
seq.
recon.
] π₯ β -
[ICCV] EPP-MVSNet: Epipolar-Assembling Based Depth Prediction for Multi-View Stereo [404] [
dep.
seq.
recon.
] π₯ β -
[ICCV] Just a Few Points are All You Need for Multi-view Stereo: A Novel Semi-supervised Learning Method for Multi-view Stereo. [
dep.
seq.
recon.
] -
[3DV] Deep Multi-View Stereo gone wild. [pytorch] [
dep.
seq.
recon.
] -
[IJCV] Unsupervised Scale-consistent Depth Learning from Video. [pytorch] [
dep.
seq.
video.
pose.
uns.
] π₯ β -
[NIPS] DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras. [pytorch] [
dep.
seq.
video.
pose.
oth.
] π₯ β -
[CVPR] Deep Two-View Structure-from-Motion Revisited. [
dep.
seq.
video.
pose.
oth.
] π₯ β -
[CVPR] Holistic 3D Scene Understanding from a Single Image with Implicit Representation [
recon.
oth.
] π₯ β -
[CVPR] From Points to Multi-Object 3D Reconstruction [
recon.
oth.
] -
[CVPR] LASR: Learning Articulated Shape Reconstruction from a Monocular Video [
recon.
video.
] π₯ β -
[NIPS] NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wild [
dep.
seq.
video.
recon.
oth.
] π₯ β
2022
-
[CVPR] Generalized Binary Search Network for Highly-Efficient Multi-View Stereo. [code] [
dep.
seq.
recon.
] -
[CVPR] Rethinking Depth Estimation for Multi-View Stereo: A Unified Representation and Focal Loss . [
dep.
seq.
recon.
] -
[CVPR] Toward Practical Self-Supervised Monocular Indoor Depth Estimation [
dep.
seq.
video.
pose.
uns.
]