「CV」 深度估计资源汇总
深度估计:根据单张图像得到深度图;
深度估计概述
Monocular Depth
· Stereo Consistency
· Depth Estimation
· Depth Completion
· Depth Fusion
1 综述
1.1 单目
-
Monocular Depth Estimation: A Survey
2019-01-27 paper -
How do neural networks see depth in single images?
2019-05-16 paper -
Monocular Depth Estimation Based On Deep Learning: An Overview
2020-07-03 paper | blog -
Deep Learning based Monocular Depth Prediction: Datasets, Methods and Applications
2022-02-18 paper
2 理论
3 单目
3.1 回归任务
3.1.1 监督
-
Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
nips 2014 2014-06-09 paper | home -
Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture
iccv 2015 2014-11-18 paper | home -
Single-Image Depth Perception in the Wild
nips 2016 2016-04-13 paper | home -
A Two-Streamed Network for Estimating Fine-Scaled Depth Maps from Single RGB Images
iccv 2017 2016-07-04 paper -
Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation
cvpr 2018 2018-03-29 paper | caffe-official -
PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network
cvpr 2018 2018-05-11 paper -
GeoNet: Geometric Neural Network for Joint Depth and Surface Normal Estimation
cvpr 2018 2020-12-13 paper | tensorflow-official
GeoNet -
Deep Ordinal Regression Network for Monocular Depth Estimation
cvpr 2018 2018-06-06 paper | caffe | pytorch
DORN -
Joint Task-Recursive Learning for Semantic Segmentation and Depth Estimation
eccv 2018 2018 paper -
Look Deeper into Depth: Monocular Depth Estimation with Semantic Booster and Attention-Driven Loss
eccv 2018 2018 paper -
Depth Esimation via Affinity Learning with Convolutional Spatial Propagation Network
eccv 2018 2018-08-01 paper | pytorch
CSPN -
SOSD-Net: Joint Semantic Object Segmentation and Depth Estimation from Monocular images
2021-01-19 paper
3.1.2 无/半监督
3.1.3 其他
- Deep Convolutional Neural Fields for Depth Estimation from a Single Image
cvpr 2015 2014-12-18 paper
3.2 分类任务
3.2.1 监督
-
Deeper Depth Prediction with Fully Convolutional Residual Networks
3dv 2016 2016-06-01 paper | tensorflow/matlab | tensorflow/matlab-official | blog
FCRN -
Monocular depth estimation using relative depth maps
cvpr 2019 2019 paper | caffe-official -
From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation
2019-07-24 paper | pytorch-tensorflow
bts -
Pattern-Affinitive Propagation across Depth, Surface Normal and Semantic Segmentation
cvpr 2019 2019-06-08 paper -
Exploiting temporal consistency for real-time video depth estimation
iccv 2019 2019-08-10 paper | pytorch
3.2.2 无/半监督
3.2.3 其他
-
Estimating Depth from Monocular Images as Classification Using Deep Fully Convolutional Residual Networks
2016-05-08 paper -
Single image depth estimation by dilated deep residual convolutional neural network and soft-weight-sum inference
2017-04-27 paper
这篇论文主要采用了跳连接来改进网络结构,跳连接的结构有利于多尺度的融合,此外还使用了空洞卷积的方法来增加感受野。
3.3 其他
4 双目
3D CycleGAN
5 其他
-
Make3D: Learning 3D Scene Structure from a Single Still Image
2014 paper
提出了 Make3D 数据集; -
Deep3D: Automatic 2D-to-3D Video Conversion with Deep Convolutional Neural Networks
2016 Paper | MXNet -
Monocular Relative Depth Perception With Web Stereo Data Supervision
cvpr 2018 2018 paper | home
提出了 ReDWeb 数据集; -
Evaluation of CNN-based Single-Image Depth Estimation Methods
eccv 2018 2018-05-03 paper
提出了 IBims-1 数据集;单反相机拍摄;并提出了一套新的评估标准; -
Learning the Depths of Moving People by Watching Frozen People
cvpr 2019 2019-04-25 paper | tensorflow-official
提出了 MannequinChallenge 数据集; -
SharpNet: Fast and Accurate Recovery of Occluding Contours in Monocular Depth Estimation
2019-05-21 paper -
Enhancing self-supervised monocular depth estimation with traditional visual odometry
2019-08-08 paper -
AI Playground: Unreal Engine-based Data Ablation Tool for Deep Learning
2020-07-13 paper | pytorch
AIP-Brown -
Learning to Recover 3D Scene Shape from a Single Image
cvpr 2021 2020-12-17 paper | pytorch-official | pytorch-compphoto
LeRes -
Towards Continual, Online, Unsupervised Depth
2021-03-02 paper | pytorch-stereo-official | pytorch-sfm-official -
Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging
cvpr 2021 2021-05-28 paper | home | pytorch-official
MiDas -
GCNDepth: Self-supervised Monocular Depth Estimation based on Graph Convolutional Network
2021-12-13 paper | pytorch-official
GCNDepth -
Global-Local Path Networks for Monocular Depth Estimation with Vertical CutDepth
2022-01-25 paper | pytorch | onnx
GLPDepth
6 顶会
6.1 CVPR 2020
-
Generating and Exploiting Probabilistic Monocular Depth Estimates
cvpr 2020 2019-06-13 paper | tensorflow-official
通用的有监督深度估计 -
Uncertainty-Aware CNNs for Depth Completion: Uncertainty from Beginning to End
cvpr 2020 2020-06-05 paper
有监督深度补全,给出了不确定性度量 -
Structure-Guided Ranking Loss for Single Image Depth Prediction
cvpr 2020 2020 paper | pyctorch-official 有监督深度估计,提出了更好的loss -
Online Depth Learning Against Forgetting in Monocular Videos
2020 paper
实时深度学习搞定深度估计 -
Du2Net: Learning Depth Estimation from Dual-Cameras and Dual-Pixels
cvpr 2020 2020-03-31 paper
附录
A 资源
文章
- 基于深度学习的单目图像深度估计
- 深度估计论文list
- https://github.com/scott89/awesome-depth
- 基于深度学习的单目深度估计综述
- 深度学习之单目深度估计 (Chapter.2):无监督学习篇
- 单目深度估计技术进展综述
- 深度学习之单目深度估计
代码
- https://github.com/nianticlabs/monodepth2(ICCV 2019)无监督
- https://github.com/dwofk/fast-depth (ICRA 2019)
- https://github.com/wangq95/KITTI_Dense_Depth 监督学习
- https://github.com/JunjH/Revisiting_Single_Depth_Estimation 监督学习
- paper with code
B 参考资料
C 数据集
数据集 | 类型 | 数量(训练/验证/测试) | 分辨率 | 说明 | 发布日期 | best model | 论文 |
---|---|---|---|---|---|---|---|
KITTI | 2个灰度相机,2个彩色相机,64线3D激光,1个GPS; 标签包含立体匹配结果、光流、场景流、深度估计、视觉测距、2D/3D目标检测、跟踪、道路/车道线检测、分割 |
GLPDepth, DIFFNet | |||||
NYUv2 | GLPDepth, Semantic-aware NN | ||||||
Make3D | GCNDepth | Make3D | |||||
Middlebury2014 | MiDas | MiDas | |||||
DIODE | 室内场景 | LeRes, AIP-Brown | |||||
ReDWeb | 室内外密集场景 | ReDWeb | |||||
Mannequin | 手持相机拍摄 | Mannequin | |||||
IBims-1 | 室内 | LeRes | IBims | ||||
WSVD | Web 视频 | ||||||
vKITTI | KITTI 的虚拟数据集,“虚拟”指的是:旋转、清晨、晴天、多云、雾天、下雨等增强,共 14G 原始 RGB 图像, 包含检测、跟踪、分割; 这一数据集的意义在于可以缓解深度信息对于光线的敏感问题 |
||||||
Cityscapes | 德国的50多个城市的户外场景,包扩左右目图像、视差深度图、相机校准、车辆测距、行人检测、目标分割等,同时也包含有类似于vKITTI的虚拟渲染场景图像; 其中简单的左视角图像、相机标定、目标分割等数据需要利用学生账号注册获取,其他数据需要联系管理员获取; |
||||||
] | |||||||
] |
Comments