SOTAVerified

Monocular Depth Estimation

Monocular Depth Estimation is the task of estimating the depth value (distance relative to the camera) of each pixel given a single (monocular) RGB image. This challenging task is a key prerequisite for determining scene understanding for applications such as 3D scene reconstruction, autonomous driving, and AR. State-of-the-art methods usually fall into one of two categories: designing a complex network that is powerful enough to directly regress the depth map, or splitting the input into bins or windows to reduce computational complexity. The most popular benchmarks are the KITTI and NYUv2 datasets. Models are typically evaluated using RMSE or absolute relative error.

Source: Defocus Deblurring Using Dual-Pixel Data

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 851–876 of 876 papers

TitleStatusHype
Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature ReconstructionCode0
Single View Stereo MatchingCode0
AdaDepth: Unsupervised Content Congruent Adaptation for Depth Estimation—0
Monocular Depth Estimation using Multi-Scale Continuous CRFs as Sequential Deep NetworksCode0
Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric ConstraintsCode0
Self-Supervised Relative Depth Learning for Urban Scene Understanding—0
Aperture Supervision for Monocular Depth Estimation—0
FLaME: Fast Lightweight Mesh Estimation Using Variational Smoothing on Delaunay Graphs—0
Automatic Discovery and Geotagging of Objects from Street View ImageryCode0
A Compromise Principle in Deep Monocular Depth Estimation—0
Fast Scene Understanding for Autonomous DrivingCode0
Monocular Depth Estimation with Hierarchical Fusion of Dilated CNNs and Soft-Weighted-Sum InferenceCode0
Recurrent Scene Parsing with Perspective Understanding in the LoopCode0
Multi-Scale Continuous CRFs as Sequential Deep Networks for Monocular Depth EstimationCode0
Semi-Supervised Deep Learning for Monocular Depth Map Prediction—0
ResearchDoom and CocoDoom: Learning Computer Vision with Games—0
Fast Robust Monocular Depth Estimation for Obstacle Detection with Fully Convolutional NetworksCode0
A Two-Streamed Network for Estimating Fine-Scaled Depth Maps from Single RGB Images—0
Depth Estimation from Single Image using Sparse Representations—0
Dense Monocular Depth Estimation in Complex Dynamic Scenes—0
Monocular Depth Estimation Using Neural Regression Forest—0
Depth from a Single Image by Harmonizing Overcomplete Local Network Predictions—0
Structured Depth Prediction in Challenging Monocular Video Sequences—0
HC-Search for Structured Prediction in Computer Vision—0
Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional ArchitectureCode0
Discrete-Continuous Depth Estimation from a Single Image—0
Show:102550
← PrevPage 18 of 18Next →

No leaderboard results yet.