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 24012425 of 2454 papers

TitleStatusHype
Semi-Supervised Monocular Depth Estimation with Left-Right Consistency Using Deep Neural NetworkCode0
D-Net: A Generalised and Optimised Deep Network for Monocular Depth EstimationCode0
UnrealROX: An eXtremely Photorealistic Virtual Reality Environment for Robotics Simulations and Synthetic Data GenerationCode0
Achieving Risk Control in Online Learning SettingsCode0
Attacking Attention of Foundation Models Disrupts Downstream TasksCode0
Introducing a Class-Aware Metric for Monocular Depth Estimation: An Automotive PerspectiveCode0
Into the Fog: Evaluating Robustness of Multiple Object TrackingCode0
Unstructured Multi-View Depth Estimation Using Mask-Based Multiplane RepresentationCode0
Discretization-Induced Dirichlet Posterior for Robust Uncertainty Quantification on RegressionCode0
Unsupervised Adversarial Depth Estimation using Cycled Generative NetworksCode0
Indoor Depth Completion with Boundary Consistency and Self-AttentionCode0
Unsupervised CNN for Single View Depth Estimation: Geometry to the RescueCode0
Digging Into Self-Supervised Monocular Depth EstimationCode0
SHADeS: Self-supervised Monocular Depth Estimation Through Non-Lambertian Image DecompositionCode0
A Systematic Performance Analysis of Deep Perceptual Loss Networks: Breaking Transfer Learning ConventionsCode0
TIE-KD: Teacher-Independent and Explainable Knowledge Distillation for Monocular Depth EstimationCode0
Index NetworkCode0
Unsupervised Depth Estimation, 3D Face Rotation and ReplacementCode0
Improving Self-Supervised Single View Depth Estimation by Masking OcclusionCode0
DFR: Depth from Rotation by Uncalibrated Image Rectification with Latitudinal Motion AssumptionCode0
Improving Neural Radiance Fields with Depth-aware Optimization for Novel View SynthesisCode0
Conf-Net: Toward High-Confidence Dense 3D Point-Cloud with Error-Map PredictionCode0
Unsupervised Domain Adaptation for Depth Prediction from ImagesCode0
SIGNet: Semantic Instance Aided Unsupervised 3D Geometry PerceptionCode0
SimC3D: A Simple Contrastive 3D Pretraining Framework Using RGB ImagesCode0
Show:102550
← PrevPage 97 of 99Next →

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