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 951975 of 2454 papers

TitleStatusHype
Monocular Depth Estimation using Multi-Scale Continuous CRFs as Sequential Deep NetworksCode0
Lightweight Monocular Depth Estimation Model by Joint End-to-End Filter pruningCode0
Light Field Compression by Residual CNN Assisted JPEGCode0
Adaptive LiDAR Sampling and Depth Completion using Ensemble VarianceCode0
Light Field Depth Estimation via Stitched Epipolar Plane ImagesCode0
L-MAGIC: Language Model Assisted Generation of Images with CoherenceCode0
DFR: Depth from Rotation by Uncalibrated Image Rectification with Latitudinal Motion AssumptionCode0
DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task ConsistencyCode0
Challenges of Multi-Modal Coreset Selection for Depth PredictionCode0
Anytime Stereo Image Depth Estimation on Mobile DevicesCode0
3D-SiamMask: Vision-Based Multi-Rotor Aerial-Vehicle Tracking for a Moving ObjectCode0
Detecting Adversarial Perturbations in Multi-Task PerceptionCode0
Learn Stereo, Infer Mono: Siamese Networks for Self-Supervised, Monocular, Depth EstimationCode0
Learning to Synthesize a 4D RGBD Light Field from a Single ImageCode0
Detail-aware multi-view stereo network for depth estimationCode0
Learning Unsupervised Multi-View Stereopsis via Robust Photometric ConsistencyCode0
DERD-Net: Learning Depth from Event-based Ray DensitiesCode0
Learning to Adapt for StereoCode0
Learning to Navigate in Complex EnvironmentsCode0
Depth self-supervision for single image novel view synthesisCode0
Learning Non-Volumetric Depth Fusion Using Successive ReprojectionsCode0
Learning Single Camera Depth Estimation using Dual-PixelsCode0
Leveraging 6DoF Pose Foundation Models For Mapping Marine Sediment BurialCode0
Long-Tailed 3D Detection via Multi-Modal FusionCode0
SharpNet: Fast and Accurate Recovery of Occluding Contours in Monocular Depth EstimationCode0
Show:102550
← PrevPage 39 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