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 151–200 of 2454 papers

TitleStatusHype
MonoCD: Monocular 3D Object Detection with Complementary DepthsCode2
CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View CompletionCode2
BinsFormer: Revisiting Adaptive Bins for Monocular Depth EstimationCode2
Mono-ViFI: A Unified Learning Framework for Self-supervised Single- and Multi-frame Monocular Depth EstimationCode2
Multi-Task Learning as Multi-Objective OptimizationCode2
DurLAR: A High-fidelity 128-channel LiDAR Dataset with Panoramic Ambient and Reflectivity Imagery for Multi-modal Autonomous Driving ApplicationsCode2
CVT-Occ: Cost Volume Temporal Fusion for 3D Occupancy PredictionCode2
Kick Back & Relax++: Scaling Beyond Ground-Truth Depth with SlowTV & CribsTVCode2
On Deep Learning for Geometric and Semantic Scene Understanding Using On-Vehicle 3D LiDARCode2
Towards Zero-Shot Scale-Aware Monocular Depth EstimationCode2
DORT: Modeling Dynamic Objects in Recurrent for Multi-Camera 3D Object Detection and TrackingCode1
Does it work outside this benchmark? Introducing the Rigid Depth Constructor tool, depth validation dataset construction in rigid scenes for the massesCode1
Domain Adaptive Semantic Segmentation with Self-Supervised Depth EstimationCode1
A Confidence-based Iterative Solver of Depths and Surface Normals for Deep Multi-view StereoCode1
Distilled Semantics for Comprehensive Scene Understanding from VideosCode1
Bidirectional Attention Network for Monocular Depth EstimationCode1
A Concise but High-performing Network for Image Guided Depth Completion in Autonomous DrivingCode1
Automated Distance Estimation for Wildlife Camera TrappingCode1
DiverseDepth: Affine-invariant Depth Prediction Using Diverse DataCode1
DS-Depth: Dynamic and Static Depth Estimation via a Fusion Cost VolumeCode1
Discrete Cosine Transform Network for Guided Depth Map Super-ResolutionCode1
Always Clear Depth: Robust Monocular Depth Estimation under Adverse WeatherCode1
Discrete Time Convolution for Fast Event-Based StereoCode1
Digging Into Uncertainty-based Pseudo-label for Robust Stereo MatchingCode1
altiro3D: Scene representation from single image and novel view synthesisCode1
Disentangling Object Motion and Occlusion for Unsupervised Multi-frame Monocular DepthCode1
All in Tokens: Unifying Output Space of Visual Tasks via Soft TokenCode1
Digging into contrastive learning for robust depth estimation with diffusion modelsCode1
Aligning Generative Denoising with Discriminative Objectives Unleashes Diffusion for Visual PerceptionCode1
2.5D Visual Relationship DetectionCode1
BiFuse: Monocular 360 Depth Estimation via Bi-Projection FusionCode1
Digging Into Self-Supervised Monocular Depth EstimationCode1
Disparity Estimation Using a Quad-Pixel SensorCode1
Dual Pixel Exploration: Simultaneous Depth Estimation and Image RestorationCode1
A Light and Tuning-free Method for Simulating Camera Motion in Video GenerationCode1
DevNet: Self-supervised Monocular Depth Learning via Density Volume ConstructionCode1
DID-M3D: Decoupling Instance Depth for Monocular 3D Object DetectionCode1
Detecting Invisible PeopleCode1
AI Playground: Unreal Engine-based Data Ablation Tool for Deep LearningCode1
DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D QueriesCode1
Differentiable Diffusion for Dense Depth Estimation from Multi-view ImagesCode1
A Hybrid Sparse-Dense Monocular SLAM System for Autonomous DrivingCode1
DEPTHOR: Depth Enhancement from a Practical Light-Weight dToF Sensor and RGB ImageCode1
ACDNet: Adaptively Combined Dilated Convolution for Monocular Panorama Depth EstimationCode1
Detaching and Boosting: Dual Engine for Scale-Invariant Self-Supervised Monocular Depth EstimationCode1
A geometry-aware deep network for depth estimation in monocular endoscopyCode1
A General and Adaptive Robust Loss FunctionCode1
DepthLab: Real-Time 3D Interaction With Depth Maps for Mobile Augmented RealityCode1
Depthformer : Multiscale Vision Transformer For Monocular Depth Estimation With Local Global Information FusionCode1
Depth Map Decomposition for Monocular Depth EstimationCode1
Show:102550
← PrevPage 4 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