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 151175 of 2454 papers

TitleStatusHype
DDP: Diffusion Model for Dense Visual PredictionCode2
Diffusion Models for Monocular Depth Estimation: Overcoming Challenging ConditionsCode2
Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language ReasoningCode2
DiffusionDepth: Diffusion Denoising Approach for Monocular Depth EstimationCode2
Boost 3D Reconstruction using Diffusion-based Monocular Camera CalibrationCode2
DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion ModelsCode2
DurLAR: A High-fidelity 128-channel LiDAR Dataset with Panoramic Ambient and Reflectivity Imagery for Multi-modal Autonomous Driving ApplicationsCode2
Monocular 3D Object Detection with Depth from MotionCode2
SceneRF: Self-Supervised Monocular 3D Scene Reconstruction with Radiance FieldsCode2
MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error PriorsCode2
CutDepth:Edge-aware Data Augmentation in Depth EstimationCode1
Detecting Invisible PeopleCode1
Cylin-Painting: Seamless 360 Panoramic Image Outpainting and BeyondCode1
Detaching and Boosting: Dual Engine for Scale-Invariant Self-Supervised Monocular Depth EstimationCode1
DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D QueriesCode1
DenseMTL: Cross-task Attention Mechanism for Dense Multi-task LearningCode1
A Confidence-based Iterative Solver of Depths and Surface Normals for Deep Multi-view StereoCode1
CT-MVSNet: Efficient Multi-View Stereo with Cross-scale TransformerCode1
CrossDTR: Cross-view and Depth-guided Transformers for 3D Object DetectionCode1
A Concise but High-performing Network for Image Guided Depth Completion in Autonomous DrivingCode1
Cross-modal transformers for infrared and visible image fusionCode1
Curvature-guided dynamic scale networks for Multi-view StereoCode1
DevNet: Self-supervised Monocular Depth Learning via Density Volume ConstructionCode1
Cost Volume Pyramid Network with Multi-strategies Range Searching for Multi-view StereoCode1
Always Clear Depth: Robust Monocular Depth Estimation under Adverse WeatherCode1
Show:102550
← PrevPage 7 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