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 601–625 of 876 papers

TitleStatusHype
BlindSpotNet: Seeing Where We Cannot See—0
False Negative Reduction in Semantic Segmentation under Domain Shift using Depth EstimationCode0
DRL-ISP: Multi-Objective Camera ISP with Deep Reinforcement Learning—0
PS^2F: Polarized Spiral Point Spread Function for Single-Shot 3D Sensing—0
Recovering Detail in 3D Shapes Using Disparity Maps—0
Monocular Depth Decomposition of Semi-Transparent Volume RenderingsCode0
0/1 Deep Neural Networks via Block Coordinate Descent—0
Analysis & Computational Complexity Reduction of Monocular and Stereo Depth Estimation TechniquesCode0
Self-Supervised Pre-training of Vision Transformers for Dense Prediction Tasks—0
Learning Monocular Depth Estimation via Selective Distillation of Stereo Knowledge—0
FisheyeDistill: Self-Supervised Monocular Depth Estimation with Ordinal Distillation for Fisheye Cameras—0
Outdoor Monocular Depth Estimation: A Research Review—0
Depth Estimation with Simplified Transformer—0
Monocular Depth Estimation Using Cues Inspired by Biological Vision SystemsCode0
Multi-Frame Self-Supervised Depth with Transformers—0
End-to-end Learning for Joint Depth and Image Reconstruction from Diffracted Rotation—0
HiMODE: A Hybrid Monocular Omnidirectional Depth Estimation Model—0
Pyramid Frequency Network with Spatial Attention Residual Refinement Module for Monocular Depth Estimation—0
Improving Monocular Visual Odometry Using Learned Depth—0
Learning Structured Gaussians to Approximate Deep Ensembles—0
Learning Optical Flow, Depth, and Scene Flow without Real-World Labels—0
DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth EstimationCode0
Learn to Adapt for Monocular Depth Estimation—0
On the Viability of Monocular Depth Pre-training for Semantic SegmentationCode0
Unsupervised Simultaneous Learning for Camera Re-Localization and Depth Estimation from Video—0
Show:102550
← PrevPage 25 of 36Next →

No leaderboard results yet.