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 401425 of 2454 papers

TitleStatusHype
EndoOmni: Zero-Shot Cross-Dataset Depth Estimation in Endoscopy by Robust Self-Learning from Noisy LabelsCode1
Estimating Image Depth in the Comics DomainCode1
Learning to Upsample by Learning to SampleCode1
LED2-Net: Monocular 360 Layout Estimation via Differentiable Depth RenderingCode1
Less is More: Consistent Video Depth Estimation with Masked Frames ModelingCode1
FDCT: Fast Depth Completion for Transparent ObjectsCode1
Deconstructing Self-Supervised Monocular Reconstruction: The Design Decisions that MatterCode1
Chitransformer: Towards Reliable Stereo From CuesCode1
Edge-aware Bidirectional Diffusion for Dense Depth Estimation from Light FieldsCode1
LightDepth: A Resource Efficient Depth Estimation Approach for Dealing with Ground Truth Sparsity via Curriculum LearningCode1
BadPart: Unified Black-box Adversarial Patch Attacks against Pixel-wise Regression TasksCode1
LiRCDepth: Lightweight Radar-Camera Depth Estimation via Knowledge Distillation and Uncertainty GuidanceCode1
ChiTransformer:Towards Reliable Stereo from CuesCode1
Deep Color Mismatch Correction In Stereoscopic 3D ImagesCode1
ACDNet: Adaptively Combined Dilated Convolution for Monocular Panorama Depth EstimationCode1
Depth and DOF Cues Make A Better Defocus Blur DetectorCode1
BaseBoostDepth: Exploiting Larger Baselines For Self-supervised Monocular Depth EstimationCode1
Channel-Wise Attention-Based Network for Self-Supervised Monocular Depth EstimationCode1
EC-Depth: Exploring the consistency of self-supervised monocular depth estimation in challenging scenesCode1
Edge-Enabled VIO with Long-Tracked Features for High-Accuracy Low-Altitude IoT NavigationCode1
Channel-Aware Distillation Transformer for Depth Estimation on Nano DronesCode1
Mesh Reconstruction from Aerial Images for Outdoor Terrain Mapping Using Joint 2D-3D LearningCode1
Manydepth2: Motion-Aware Self-Supervised Multi-Frame Monocular Depth Estimation in Dynamic ScenesCode1
MGNet: Monocular Geometric Scene Understanding for Autonomous DrivingCode1
Dyna-DM: Dynamic Object-aware Self-supervised Monocular Depth MapsCode1
Show:102550
← PrevPage 17 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