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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 201–250 of 2454 papers

TitleStatusHype
ACDNet: Adaptively Combined Dilated Convolution for Monocular Panorama Depth EstimationCode1
Camera-based 3D Semantic Scene Completion with Sparse Guidance NetworkCode1
Dual Transfer Learning for Event-based End-task Prediction via Pluggable Event to Image TranslationCode1
Edge-aware Bidirectional Diffusion for Dense Depth Estimation from Light FieldsCode1
A geometry-aware deep network for depth estimation in monocular endoscopyCode1
BadPart: Unified Black-box Adversarial Patch Attacks against Pixel-wise Regression TasksCode1
DiverseDepth: Affine-invariant Depth Prediction Using Diverse DataCode1
BaseBoostDepth: Exploiting Larger Baselines For Self-supervised Monocular Depth EstimationCode1
A General and Adaptive Robust Loss FunctionCode1
DORT: Modeling Dynamic Objects in Recurrent for Multi-Camera 3D Object Detection and TrackingCode1
Distilled Semantics for Comprehensive Scene Understanding from VideosCode1
Bayes' Rays: Uncertainty Quantification for Neural Radiance FieldsCode1
Disentangling Object Motion and Occlusion for Unsupervised Multi-frame Monocular DepthCode1
A Hybrid Sparse-Dense Monocular SLAM System for Autonomous DrivingCode1
Discrete Time Convolution for Fast Event-Based StereoCode1
Disparity Estimation Using a Quad-Pixel SensorCode1
Digging Into Uncertainty-based Pseudo-label for Robust Stereo MatchingCode1
Discrete Cosine Transform Network for Guided Depth Map Super-ResolutionCode1
Automated Distance Estimation for Wildlife Camera TrappingCode1
Does it work outside this benchmark? Introducing the Rigid Depth Constructor tool, depth validation dataset construction in rigid scenes for the massesCode1
BEV-LGKD: A Unified LiDAR-Guided Knowledge Distillation Framework for BEV 3D Object DetectionCode1
BEVNeXt: Reviving Dense BEV Frameworks for 3D Object DetectionCode1
DID-M3D: Decoupling Instance Depth for Monocular 3D Object DetectionCode1
E-DSSR: Efficient Dynamic Surgical Scene Reconstruction with Transformer-based Stereoscopic Depth PerceptionCode1
DevNet: Self-supervised Monocular Depth Learning via Density Volume ConstructionCode1
Aligning Generative Denoising with Discriminative Objectives Unleashes Diffusion for Visual PerceptionCode1
Beyond Image to Depth: Improving Depth Prediction using EchoesCode1
Differentiable Diffusion for Dense Depth Estimation from Multi-view ImagesCode1
All in Tokens: Unifying Output Space of Visual Tasks via Soft TokenCode1
Bi3D: Stereo Depth Estimation via Binary ClassificationsCode1
Bidirectional Attention Network for Monocular Depth EstimationCode1
BiFuse: Monocular 360 Depth Estimation via Bi-Projection FusionCode1
Digging into contrastive learning for robust depth estimation with diffusion modelsCode1
Energy-Efficient Adaptive 3D SensingCode1
Detaching and Boosting: Dual Engine for Scale-Invariant Self-Supervised Monocular Depth EstimationCode1
AeDet: Azimuth-invariant Multi-view 3D Object DetectionCode1
EPI-based Oriented Relation Networks for Light Field Depth EstimationCode1
ES-Net: An Efficient Stereo Matching NetworkCode1
A Concise but High-performing Network for Image Guided Depth Completion in Autonomous DrivingCode1
Can Language Understand Depth?Code1
Excavating the Potential Capacity of Self-Supervised Monocular Depth EstimationCode1
Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuningCode1
Detecting Invisible PeopleCode1
A Confidence-based Iterative Solver of Depths and Surface Normals for Deep Multi-view StereoCode1
BodySLAM: A Generalized Monocular Visual SLAM Framework for Surgical ApplicationsCode1
Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary CellsCode1
CaFNet: A Confidence-Driven Framework for Radar Camera Depth EstimationCode1
DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D QueriesCode1
Digging Into Self-Supervised Monocular Depth EstimationCode1
Domain Adaptive Semantic Segmentation with Self-Supervised Depth EstimationCode1
Show:102550
← PrevPage 5 of 50Next →
All datasetsStanford2D3D PanoramicNYU-Depth V2DCMeBDthequeScanNetV2Cityscapes testDIODEKITTI 2015Mars DTM EstimationScanNet4D Light Field DatasetKITTI Eigen split

Benchmark Results

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