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 1601–1650 of 2454 papers

TitleStatusHype
Composite Learning for Robust and Effective Dense Predictions—0
Computing Egomotion with Local Loop Closures for Egocentric Videos—0
Confidence-Aware RGB-D Face Recognition via Virtual Depth Synthesis—0
Confidence Guided Stereo 3D Object Detection with Split Depth Estimation—0
Configurable Holography: Towards Display and Scene Adaptation—0
Connecting the Dots: Learning Representations for Active Monocular Depth Estimation—0
Consistent Depth of Moving Objects in Video—0
Consistent Depth Prediction for Transparent Object Reconstruction from RGB-D Camera—0
Consistent Depth Prediction under Various Illuminations using Dilated Cross Attention—0
Content-Aware Inter-Scale Cost Aggregation for Stereo Matching—0
Continuous Online Extrinsic Calibration of Fisheye Camera and LiDAR—0
ContrastAlign: Toward Robust BEV Feature Alignment via Contrastive Learning for Multi-Modal 3D Object Detection—0
Contrastive Mutual Information Maximization for Binary Neural Networks—0
Contrastive Unsupervised Learning of World Model with Invariant Causal Features—0
ConvNets vs. Transformers: Whose Visual Representations are More Transferable?—0
Convolutional neural network-based regression for depth prediction in digital holography—0
CORE: Co-planarity Regularized Monocular Geometry Estimation with Weak Supervision—0
Co-training for Deep Object Detection: Comparing Single-modal and Multi-modal Approaches—0
Coupled Depth Learning—0
CReaM: Condensed Real-time Models for Depth Prediction using Convolutional Neural Networks—0
CRF360D: Monocular 360 Depth Estimation via Spherical Fully-Connected CRFs—0
CroMo: Cross-Modal Learning for Monocular Depth Estimation—0
Cross-Dimensional Refined Learning for Real-Time 3D Visual Perception from Monocular Video—0
CrossFusion: Interleaving Cross-modal Complementation for Noise-resistant 3D Object Detection—0
Cross-spectral Gated-RGB Stereo Depth Estimation—0
Cross-View Completion Models are Zero-shot Correspondence Estimators—0
CUBE360: Learning Cubic Field Representation for Monocular 360 Depth Estimation for Virtual Reality—0
D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry—0
DAP-LED: Learning Degradation-Aware Priors with CLIP for Joint Low-light Enhancement and Deblurring—0
Dark Channel-Assisted Depth-from-Defocus from a Single Image—0
DarSwin: Distortion Aware Radial Swin Transformer—0
DarSwin-Unet: Distortion Aware Encoder-Decoder Architecture—0
Data-Driven Method for Enhanced Corrosion Assessment of Reinforced Concrete Structures—0
Dense Depth Distillation with Out-of-Distribution Simulated Images—0
DATAP-SfM: Dynamic-Aware Tracking Any Point for Robust Structure from Motion in the Wild—0
DB3D-L: Depth-aware BEV Feature Transformation for Accurate 3D Lane Detection—0
DCIRNet: Depth Completion with Iterative Refinement for Dexterous Grasping of Transparent and Reflective Objects—0
DCPI-Depth: Explicitly Infusing Dense Correspondence Prior to Unsupervised Monocular Depth Estimation—0
DDOS: The Drone Depth and Obstacle Segmentation Dataset—0
DD-VNB: A Depth-based Dual-Loop Framework for Real-time Visually Navigated Bronchoscopy—0
Dead Time Compensation for High-Flux Ranging—0
Decoder Modulation for Indoor Depth Completion—0
Decomposition-based and Interference Perception for Infrared and Visible Image Fusion in Complex Scenes—0
Deep 3D Pan via adaptive "t-shaped" convolutions with global and local adaptive dilations—0
Deep 3D Pan via Local adaptive "t-shaped" convolutions with global and local adaptive dilations—0
Deep Anti-aliasing of Whole Focal Stack Using Slice Spectrum—0
Deep Classification Network for Monocular Depth Estimation—0
Deep Convolutional Neural Fields for Depth Estimation from a Single Image—0
Deep cross-domain building extraction for selective depth estimation from oblique aerial imagery—0
Deep Depth From Aberration Map—0
Show:102550
← PrevPage 33 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