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 76–100 of 876 papers

TitleStatusHype
A Practical Stereo Depth System for Smart GlassesCode1
Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary CellsCode1
DepthLab: Real-Time 3D Interaction With Depth Maps for Mobile Augmented RealityCode1
Advancing Self-supervised Monocular Depth Learning with Sparse LiDARCode1
ENRICH: Multi-purposE dataset for beNchmaRking In Computer vision and pHotogrammetryCode1
A benchmark with decomposed distribution shifts for 360 monocular depth estimationCode1
An intelligent modular real-time vision-based system for environment perceptionCode1
Depth Map Decomposition for Monocular Depth EstimationCode1
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text AlignmentCode1
Depthformer : Multiscale Vision Transformer For Monocular Depth Estimation With Local Global Information FusionCode1
Depth Map Prediction from a Single Image using a Multi-Scale Deep NetworkCode1
DELTAS: Depth Estimation by Learning Triangulation And densification of Sparse pointsCode1
Depth Attention for Robust RGB TrackingCode1
Depth Estimation from Monocular Images and Sparse radar using Deep Ordinal Regression NetworkCode1
Detaching and Boosting: Dual Engine for Scale-Invariant Self-Supervised Monocular Depth EstimationCode1
Excavating the Potential Capacity of Self-Supervised Monocular Depth EstimationCode1
RePoseD: Efficient Relative Pose Estimation With Known Depth InformationCode1
Deep Two-View Structure-from-Motion RevisitedCode1
DeFeat-Net: General Monocular Depth via Simultaneous Unsupervised Representation LearningCode1
Depth and DOF Cues Make A Better Defocus Blur DetectorCode1
Boosting Omnidirectional Stereo Matching with a Pre-trained Depth Foundation ModelCode1
360MonoDepth: High-Resolution 360° Monocular Depth EstimationCode1
Boosting Light-Weight Depth Estimation Via Knowledge DistillationCode1
3DPPE: 3D Point Positional Encoding for Multi-Camera 3D Object Detection TransformersCode1
3D-PL: Domain Adaptive Depth Estimation with 3D-aware Pseudo-LabelingCode1
Show:102550
← PrevPage 4 of 36Next →

No leaderboard results yet.