SOTAVerified

Depth Estimation

Depth Estimation is the task of measuring the distance of each pixel relative to the camera. Depth is extracted from either monocular (single) or stereo (multiple views of a scene) images. Traditional methods use multi-view geometry to find the relationship between the images. Newer methods can directly estimate depth by minimizing the regression loss, or by learning to generate a novel view from a sequence. The most popular benchmarks are KITTI and NYUv2. Models are typically evaluated according to a RMS metric.

Source: DIODE: A Dense Indoor and Outdoor DEpth Dataset

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 2051–2100 of 2454 papers

TitleStatusHype
Vision: A Deep Learning Approach to provide walking assistance to the visually impairedCode0
360SD-Net: 360° Stereo Depth Estimation with Learnable Cost VolumeCode0
MonSter: Awakening the Mono in Stereo—0
On the Benefit of Adversarial Training for Monocular Depth EstimationCode0
Deep Classification Network for Monocular Depth Estimation—0
Unsupervised High-Resolution Depth Learning From Videos With Dual Networks—0
Octave Deep Plane-Sweeping Network: Reducing Spatial Redundancy for Learning-Based Plane-Sweeping StereoCode0
Joint Image and Depth Estimation with Mask-Based Lensless Cameras—0
ClearGrasp: 3D Shape Estimation of Transparent Objects for ManipulationCode0
Robust Semi-Supervised Monocular Depth Estimation with Reprojected Distances—0
A Neural Network for Detailed Human Depth Estimation from a Single ImageCode0
Deep 3D Pan via adaptive "t-shaped" convolutions with global and local adaptive dilations—0
Monocular Piecewise Depth Estimation in Dynamic Scenes by Exploiting Superpixel Relations—0
Digging Into Self-Supervised Monocular Depth EstimationCode0
Spatial Correspondence With Generative Adversarial Network: Learning Depth From Monocular Videos—0
SynDeMo: Synergistic Deep Feature Alignment for Joint Learning of Depth and Ego-Motion—0
Deep Depth From Aberration Map—0
Nighttime Stereo Depth Estimation using Joint Translation-Stereo Learning: Light Effects and Uninformative RegionsCode0
SteReFo: Efficient Image Refocusing with Stereo Vision—0
Global-Local Network for Learning Depth with Very Sparse Supervision—0
Efficient Surface-Aware Semi-Global Matching with Multi-View Plane-Sweep Sampling—0
Self-Supervised Monocular Depth HintsCode0
Learning to Think Outside the Box: Wide-Baseline Light Field Depth Estimation with EPI-Shift—0
Progressive Fusion for Unsupervised Binocular Depth Estimation using Cycled NetworksCode0
Spherical View Synthesis for Self-Supervised 360 Depth EstimationCode0
Task-Aware Monocular Depth Estimation for 3D Object DetectionCode0
Temporally Consistent Depth Prediction with Flow-Guided Memory Units—0
Deep Robotic Prediction with hierarchical RGB-D Fusion—0
3D Ken Burns Effect from a Single ImageCode0
Flow-Motion and Depth Network for Monocular Stereo and BeyondCode0
Structure-Attentioned Memory Network for Monocular Depth Estimation—0
Unsupervised Domain Adaptation for Depth Prediction from ImagesCode0
Robust Full-FoV Depth Estimation in Tele-wide Camera System—0
Auxiliary Learning for Deep Multi-task Learning—0
Depth Map Estimation for Free-Viewpoint Television—0
Unsupervised Video Depth Estimation Based on Ego-motion and Disparity Consensus—0
Deep Coarse-to-fine Dense Light Field Reconstruction with Flexible Sampling and Geometry-aware FusionCode0
UASOL, a large-scale high-resolution outdoor stereo dataset—0
Improving Self-Supervised Single View Depth Estimation by Masking OcclusionCode0
Sequential Adversarial Learning for Self-Supervised Deep Visual Odometry—0
Indoor Depth Completion with Boundary Consistency and Self-AttentionCode0
n-MeRCI: A new Metric to Evaluate the Correlation Between Predictive Uncertainty and True Error—0
In defense of OSVOS—0
Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning—0
OmniMVS: End-to-End Learning for Omnidirectional Stereo MatchingCode0
Task-Assisted Domain Adaptation with Anchor Tasks—0
Structured Coupled Generative Adversarial Networks for Unsupervised Monocular Depth Estimation—0
To complete or to estimate, that is the question: A Multi-Task Approach to Depth Completion and Monocular Depth Estimation—0
Index NetworkCode0
Exploiting temporal consistency for real-time video depth estimationCode0
Show:102550
← PrevPage 42 of 50Next →
All datasetsStanford2D3D PanoramicNYU-Depth V2DCMeBDthequeScanNetV2Cityscapes testDIODEKITTI 2015Mars DTM EstimationScanNet4D Light Field DatasetKITTI Eigen split

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1OmniDepthRMSE0.62—Unverified
2SphereDepthRMSE0.45—Unverified
3Jin et al.RMSE0.42—Unverified
4BiFuse with fusionRMSE0.41—Unverified
5HoHoNet (ResNet-101)RMSE0.38—Unverified
6PanoDepthRMSE0.37—Unverified
7BiFuse++RMSE0.37—Unverified
8UniFuse with fusionRMSE0.37—Unverified
9DisConvRMSE0.37—Unverified
10SliceNetRMSE0.37—Unverified
#ModelMetricClaimedVerifiedStatus
1A2JmAP8.61—Unverified
2PAD-NetRMS0.79—Unverified
3MS-CRFRMS0.59—Unverified
4DORNRMS0.51—Unverified
5FreeformRMS0.43—Unverified
6Optimized, freeformRMS0.43—Unverified
7VNLRMS0.42—Unverified
8BTSRMS0.41—Unverified
9TransDepth (AGD+ ViT)RMS0.37—Unverified
10AdaBinsRMS0.36—Unverified
#ModelMetricClaimedVerifiedStatus
1T2NetAbs Rel0.35—Unverified
2MIDASAbs Rel0.31—Unverified
3Bhattacharjee et al.Abs Rel0.25—Unverified
#ModelMetricClaimedVerifiedStatus
1T2NetAbs Rel0.49—Unverified
2MIDASAbs Rel0.42—Unverified
3Bhattacharjee et al.Abs Rel0.38—Unverified
#ModelMetricClaimedVerifiedStatus
1LeReSabsolute relative error0.1—Unverified
2DELTASabsolute relative error0.09—Unverified
3Distill Any Depthabsolute relative error0.04—Unverified
#ModelMetricClaimedVerifiedStatus
1SDC-DepthRMSE6.92—Unverified
2SwinMTLRMSE6.35—Unverified
#ModelMetricClaimedVerifiedStatus
1AIP-BrownDelta < 1.250.36—Unverified
2LeResDelta < 1.250.23—Unverified
#ModelMetricClaimedVerifiedStatus
1H-Net (Ours)Absolute relative error (AbsRel)0.09—Unverified
2H-Net (Ours) Full EigenAbsolute relative error (AbsRel)0.08—Unverified
#ModelMetricClaimedVerifiedStatus
1GLPDepthDelta < 1.250.43—Unverified
2SRDINET (Model A)Delta < 1.250.4—Unverified
#ModelMetricClaimedVerifiedStatus
1Atlas (finetuned)RMSE0.17—Unverified
2Atlas (plain)RMSE0.17—Unverified
#ModelMetricClaimedVerifiedStatus
1LFattNetBadPix(0.01)17.23—Unverified
#ModelMetricClaimedVerifiedStatus
1LightDepthNumber of parameters (M)42.6—Unverified
#ModelMetricClaimedVerifiedStatus
1UniFuseAbs Rel0.11—Unverified
#ModelMetricClaimedVerifiedStatus
1X-TC (Cross-Task Consistency)L1 error1.63—Unverified