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

Showing 601650 of 2454 papers

TitleStatusHype
Monocular Depth Estimation via Listwise Ranking using the Plackett-Luce ModelCode1
DepthLab: Real-Time 3D Interaction With Depth Maps for Mobile Augmented RealityCode1
Learning Monocular Dense Depth from EventsCode1
What Can You Learn from Your Muscles? Learning Visual Representation from Human InteractionsCode1
Unsupervised Learning of Depth and Ego-Motion from Cylindrical Panoramic Video with Applications for Virtual RealityCode1
Spatially-Variant CNN-based Point Spread Function Estimation for Blind Deconvolution and Depth Estimation in Optical MicroscopyCode1
Unsupervised Monocular Depth Estimation for Night-time Images using Adversarial Domain Feature AdaptationCode1
Depth Estimation from Monocular Images and Sparse Radar DataCode1
Adaptive confidence thresholding for monocular depth estimationCode1
View-consistent 4D Light Field Depth EstimationCode1
Multi-Loss Weighting with Coefficient of VariationsCode1
Bidirectional Attention Network for Monocular Depth EstimationCode1
VR-Caps: A Virtual Environment for Capsule EndoscopyCode1
One Shot 3D PhotographyCode1
Single-Image Depth Prediction Makes Feature Matching EasierCode1
Visibility-aware Multi-view Stereo NetworkCode1
Self-Supervised Learning for Monocular Depth Estimation from Aerial ImageryCode1
Reversing the cycle: self-supervised deep stereo through enhanced monocular distillationCode1
Forget About the LiDAR: Self-Supervised Depth Estimators with MED Probability VolumesCode1
Learning Stereo from Single ImagesCode1
Multi-Loss Rebalancing Algorithm for Monocular Depth EstimationCode1
P²Net: Patch-match and Plane-regularization for Unsupervised Indoor Depth EstimationCode1
Single-Image Depth Prediction Makes Feature Matching EasierCode1
Deep Depth Estimation from Visual-Inertial SLAMCode1
Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware Multi-view Geometry ConsistencyCode1
Feature-metric Loss for Self-supervised Learning of Depth and EgomotionCode1
Multi-person 3D Pose Estimation in Crowded Scenes Based on Multi-View GeometryCode1
Non-Local Spatial Propagation Network for Depth CompletionCode1
HDNet: Human Depth Estimation for Multi-Person Camera-Space LocalizationCode1
Defocus Blur Detection via Depth DistillationCode1
P^2Net: Patch-match and Plane-regularization for Unsupervised Indoor Depth EstimationCode1
Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic GuidanceCode1
360^ Depth Estimation from Multiple Fisheye Images with Origami Crown Representation of IcosahedronCode1
AI Playground: Unreal Engine-based Data Ablation Tool for Deep LearningCode1
Continual Adaptation for Deep StereoCode1
EPI-based Oriented Relation Networks for Light Field Depth EstimationCode1
Camera Pose Matters: Improving Depth Prediction by Mitigating Pose Distribution BiasCode1
Wasserstein Distances for Stereo Disparity EstimationCode1
EndoSLAM Dataset and An Unsupervised Monocular Visual Odometry and Depth Estimation Approach for Endoscopic Videos: Endo-SfMLearnerCode1
MTStereo 2.0: improved accuracy of stereo depth estimation withMax-treesCode1
Regression Prior NetworksCode1
Targeted Adversarial Perturbations for Monocular Depth PredictionCode1
Real-time single image depth perception in the wild with handheld devicesCode1
Robust Learning Through Cross-Task ConsistencyCode1
SharinGAN: Combining Synthetic and Real Data for Unsupervised Geometry EstimationCode1
Auto-Rectify Network for Unsupervised Indoor Depth EstimationCode1
BiFuse: Monocular 360 Depth Estimation via Bi-Projection FusionCode1
Upgrading Optical Flow to 3D Scene Flow Through Optical ExpansionCode1
Robust Learning Through Cross-Task ConsistencyCode1
Height and Uprightness Invariance for 3D Prediction From a Single ViewCode1
Show:102550
← PrevPage 13 of 50Next →

Benchmark Results

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