Browse SoTA > Computer Vision > Depth Estimation > Monocular Depth Estimation

Monocular Depth Estimation

65 papers with code · Computer Vision
Subtask of Depth Estimation

The Monocular Depth Estimation is the task of estimating scene depth using a single image.

Source: Defocus Deblurring Using Dual-Pixel Data

Benchmarks

Latest papers with code

Learning Stereo from Single Images

4 Aug 2020nianticlabs/stereo-from-mono

We propose that it is unnecessary to have such a high reliance on ground truth depths or even corresponding stereo pairs.

MONOCULAR DEPTH ESTIMATION STEREO MATCHING

75
04 Aug 2020

Regression Prior Networks

20 Jun 2020JanRocketMan/regression-prior-networks

Prior Networks are a recently developed class of models which yield interpretable measures of uncertainty and have been shown to outperform state-of-the-art ensemble approaches on a range of tasks.

MONOCULAR DEPTH ESTIMATION

9
20 Jun 2020

Unsupervised Depth Learning in Challenging Indoor Video: Weak Rectification to Rescue

4 Jun 2020JiawangBian/Unsupervised-Indoor-Depth

However, the excellent results have mostly been obtained in street-scene driving scenarios, and such methods often fail in other settings, particularly indoor videos taken by handheld devices, in which case the ego-motion is often degenerate, i. e., the rotation dominates the translation.

MONOCULAR DEPTH ESTIMATION SELF-SUPERVISED LEARNING

43
04 Jun 2020

Self-Supervised Monocular Scene Flow Estimation

CVPR 2020 visinf/self-mono-sf

Our model achieves state-of-the-art accuracy among unsupervised/self-supervised learning approaches to monocular scene flow, and yields competitive results for the optical flow and monocular depth estimation sub-tasks.

MONOCULAR DEPTH ESTIMATION OPTICAL FLOW ESTIMATION SCENE FLOW ESTIMATION SELF-SUPERVISED LEARNING

96
01 Jun 2020

Toward Hierarchical Self-Supervised Monocular Absolute Depth Estimation for Autonomous Driving Applications

12 Apr 2020TJ-IPLab/DNet

Our contributions are twofold: a) a novel dense connected prediction (DCP) layer is proposed to provide better object-level depth estimation and b) specifically for autonomous driving scenarios, dense geometrical constrains (DGC) is introduced so that precise scale factor can be recovered without additional cost for autonomous vehicles.

AUTONOMOUS DRIVING MONOCULAR DEPTH ESTIMATION

2
12 Apr 2020

Self-Supervised Monocular Scene Flow Estimation

CVPR 2020 visinf/self-mono-sf

Our model achieves state-of-the-art accuracy among unsupervised/self-supervised learning approaches to monocular scene flow, and yields competitive results for the optical flow and monocular depth estimation sub-tasks.

MONOCULAR DEPTH ESTIMATION OPTICAL FLOW ESTIMATION SCENE FLOW ESTIMATION SELF-SUPERVISED LEARNING

96
08 Apr 2020

DeFeat-Net: General Monocular Depth via Simultaneous Unsupervised Representation Learning

CVPR 2020 jspenmar/DeFeat-Net

In the current monocular depth research, the dominant approach is to employ unsupervised training on large datasets, driven by warped photometric consistency.

MONOCULAR DEPTH ESTIMATION UNSUPERVISED REPRESENTATION LEARNING

8
30 Mar 2020

Holopix50k: A Large-Scale In-the-wild Stereo Image Dataset

arXiv 2020 leiainc/holopix50k

With the mass-market adoption of dual-camera mobile phones, leveraging stereo information in computer vision has become increasingly important.

MONOCULAR DEPTH ESTIMATION SUPER-RESOLUTION

92
25 Mar 2020

Unsupervised Learning of Depth, Optical Flow and Pose with Occlusion from 3D Geometry

arXiv 2020 guangmingw/DOPlearning

In the occluded region, as depth and camera motion can provide more reliable motion estimation, they can be used to instruct unsupervised learning of flow.

AUTONOMOUS DRIVING DEPTH AND CAMERA MOTION MONOCULAR DEPTH ESTIMATION MONOCULAR VISUAL ODOMETRY MOTION ESTIMATION OPTICAL FLOW ESTIMATION

25
02 Mar 2020