Depth Estimation

324 papers with code • 8 benchmarks • 40 datasets

Depth Estimation is a crucial step towards inferring scene geometry from 2D images. The goal in monocular Depth Estimation is to predict the depth value of each pixel, given only a single RGB image as input.

Source: DIODE: A Dense Indoor and Outdoor DEpth Dataset

Greatest papers with code

Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraints

tensorflow/models CVPR 2018

We present a novel approach for unsupervised learning of depth and ego-motion from monocular video.

Depth And Camera Motion

Unsupervised Monocular Depth Learning in Dynamic Scenes

google-research/google-research 30 Oct 2020

We present a method for jointly training the estimation of depth, ego-motion, and a dense 3D translation field of objects relative to the scene, with monocular photometric consistency being the sole source of supervision.

Depth Estimation

Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Cameras

google-research/google-research ICCV 2019

We present a novel method for simultaneous learning of depth, egomotion, object motion, and camera intrinsics from monocular videos, using only consistency across neighboring video frames as supervision signal.

Depth Estimation

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

A General and Adaptive Robust Loss Function

google-research/google-research CVPR 2019

We present a generalization of the Cauchy/Lorentzian, Geman-McClure, Welsch/Leclerc, generalized Charbonnier, Charbonnier/pseudo-Huber/L1-L2, and L2 loss functions.

Image Generation

Learning to Navigate in Complex Environments

deepmind/lab 11 Nov 2016

Learning to navigate in complex environments with dynamic elements is an important milestone in developing AI agents.

Depth Estimation General Classification