Depth Estimation Edit Task

Computer Vision

299

papers with code

benchmarks

datasets

About
Edit

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

Benchmarks

Add a Result

DATASET	BEST METHOD	PAPER TITLE	COMPARE
NYU-Depth V2	Semantic-aware NN	3D Ken Burns Effect from a Single Image	See all
ScanNet	Atlas (plain)	Atlas: End-to-End 3D Scene Reconstruction from Posed Images	See all
ScanNetV2	DELTAS	DELTAS: Depth Estimation by Learning Triangulation And densification of Sparse points	See all
4D Light Field Dataset	LFattNet	Attention-based View Selection Networks for Light-field Disparity Estimation	See all
Taskonomy	X-TC (Cross-Task Consistency)	Robust Learning Through Cross-Task Consistency	See all
Cityscapes test	SDC-Depth	SDC-Depth: Semantic Divide-and-Conquer Network for Monocular Depth Estimation	See all
DIODE	AIP-Brown	AI Playground: Unreal Engine-based Data Ablation Tool for Deep Learning	See all

Subtasks

Monocular Depth Estimation

5 benchmarks

111 papers with code

Stereo Depth Estimation

2 benchmarks

19 papers with code

Depth And Camera Motion

12 papers with code

3D Depth Estimation

6 papers with code

Stereo-LiDAR Fusion

1 benchmark

6 papers with code

See all 8 subtasks

Datasets

ScanNet

Taskonomy

DIODE

Cityscapes

NYUv2

See all 36 datasets

Greatest papers with code

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

CVPR 2018 • tensorflow/models •

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

DEPTH AND CAMERA MOTION

69,441

Paper
Code

Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videos

15 Nov 2018 • tensorflow/models •

Models and examples built with TensorFlow

Ranked #22 on Monocular Depth Estimation on KITTI Eigen split

DEPTH AND CAMERA MOTION MOTION ESTIMATION ROBOT NAVIGATION

65,338

Paper
Code

Unsupervised Monocular Depth Learning in Dynamic Scenes

30 Oct 2020 • google-research/google-research •

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

16,924

Paper
Code

Learning Single Camera Depth Estimation using Dual-Pixels

ICCV 2019 • google-research/google-research •

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

16,922

Paper
Code

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

ICCV 2019 • google-research/google-research •

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

16,922

Paper
Code

A General and Adaptive Robust Loss Function

CVPR 2019 • google-research/google-research •

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

16,922

Paper
Code