Monocular Depth Estimation

125 papers with code • 8 benchmarks • 13 datasets

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

Source: Defocus Deblurring Using Dual-Pixel Data

Greatest papers with code

Learning Single Camera Depth Estimation using Dual-Pixels

google-research/google-research ICCV 2019

Using our approach, existing monocular depth estimation techniques can be effectively applied to dual-pixel data, and much smaller models can be constructed that still infer high quality depth.

Monocular Depth Estimation

High Quality Monocular Depth Estimation via Transfer Learning

ialhashim/DenseDepth 31 Dec 2018

Accurate depth estimation from images is a fundamental task in many applications including scene understanding and reconstruction.

Monocular Depth Estimation Transfer Learning

Vision Transformers for Dense Prediction

intel-isl/MiDaS 24 Mar 2021

We introduce dense vision transformers, an architecture that leverages vision transformers in place of convolutional networks as a backbone for dense prediction tasks.

 Ranked #1 on Monocular Depth Estimation on NYU-Depth V2 (using extra training data)

Monocular Depth Estimation Semantic Segmentation

Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer

intel-isl/MiDaS 2 Jul 2019

In particular, we propose a robust training objective that is invariant to changes in depth range and scale, advocate the use of principled multi-objective learning to combine data from different sources, and highlight the importance of pretraining encoders on auxiliary tasks.

Monocular Depth Estimation

GIMP-ML: Python Plugins for using Computer Vision Models in GIMP

kritiksoman/GIMP-ML 27 Apr 2020

Apart from these, several image manipulation techniques using these plugins have been compiled and demonstrated in the YouTube channel (https://youtube. com/user/kritiksoman) with the objective of demonstrating the use-cases for machine learning based image modification.

Colorization Deblurring +8

Semantically-Guided Representation Learning for Self-Supervised Monocular Depth

TRI-ML/packnet-sfm ICLR 2020

Instead of using semantic labels and proxy losses in a multi-task approach, we propose a new architecture leveraging fixed pretrained semantic segmentation networks to guide self-supervised representation learning via pixel-adaptive convolutions.

Monocular Depth Estimation Representation Learning +2