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 2301–2350 of 2454 papers

TitleStatusHype
Monocular Depth Estimation using Multi-Scale Continuous CRFs as Sequential Deep NetworksCode0
Monocular Depth Estimation Using Cues Inspired by Biological Vision SystemsCode0
An Online Adaptation Method for Robust Depth Estimation and Visual Odometry in the Open WorldCode0
Estimating Depth from RGB and Sparse SensingCode0
SceneNet RGB-D: 5M Photorealistic Images of Synthetic Indoor Trajectories with Ground TruthCode0
Monocular Depth Decomposition of Semi-Transparent Volume RenderingsCode0
Estimated Depth Map Helps Image ClassificationCode0
Monocular 3D Object Detection with Pseudo-LiDAR Point CloudCode0
Back to the Color: Learning Depth to Specific Color Transformation for Unsupervised Depth EstimationCode0
VGLD: Visually-Guided Linguistic Disambiguation for Monocular Depth Scale RecoveryCode0
SDGOCC: Semantic and Depth-Guided Bird's-Eye View Transformation for 3D Multimodal Occupancy PredictionCode0
Adaptive LiDAR Sampling and Depth Completion using Ensemble VarianceCode0
D^3epth: Self-Supervised Depth Estimation with Dynamic Mask in Dynamic ScenesCode0
SweepNet: Wide-baseline Omnidirectional Depth EstimationCode0
Sea-ing in Low-lightCode0
EPP-MVSNet: Epipolar-Assembling Based Depth Prediction for Multi-View StereoCode0
MGNiceNet: Unified Monocular Geometric Scene UnderstandingCode0
EPINET: A Fully-Convolutional Neural Network Using Epipolar Geometry for Depth from Light Field ImagesCode0
Seeing Far in the Dark with Patterned FlashCode0
Auxiliary Tasks in Multi-task LearningCode0
SeGAN: Segmenting and Generating the InvisibleCode0
Video Depth Estimation by Fusing Flow-to-Depth ProposalsCode0
SelectionConv: Convolutional Neural Networks for Non-rectilinear Image DataCode0
A Neural Network for Detailed Human Depth Estimation from a Single ImageCode0
CVCP-Fusion: On Implicit Depth Estimation for 3D Bounding Box PredictionCode0
MetricGold: Leveraging Text-To-Image Latent Diffusion Models for Metric Depth EstimationCode0
METER: a mobile vision transformer architecture for monocular depth estimationCode0
Cut-and-Splat: Leveraging Gaussian Splatting for Synthetic Data GenerationCode0
Maximum Likelihood Uncertainty Estimation: Robustness to OutliersCode0
Self-Supervised 3D Keypoint Learning for Ego-motion EstimationCode0
Enhancing Underwater Imaging with 4-D Light Fields: Dataset and MethodCode0
Mapped ConvolutionsCode0
Automatic Discovery and Geotagging of Objects from Street View ImageryCode0
Creative Flow+ DatasetCode0
Long-Tailed 3D Detection via Multi-Modal FusionCode0
Co-SemDepth: Fast Joint Semantic Segmentation and Depth Estimation on Aerial ImagesCode0
Enhancing Monocular Depth Estimation with Multi-Source Auxiliary TasksCode0
T2Net: Synthetic-to-Realistic Translation for Solving Single-Image Depth Estimation TasksCode0
L-MAGIC: Language Model Assisted Generation of Images with CoherenceCode0
Correlation of Object Detection Performance with Visual Saliency and Depth EstimationCode0
EndoLRMGS: Complete Endoscopic Scene Reconstruction combining Large Reconstruction Modelling and Gaussian SplattingCode0
Lightweight Monocular Depth Estimation Model by Joint End-to-End Filter pruningCode0
Light Field Depth Estimation via Stitched Epipolar Plane ImagesCode0
EndoGaussian: Real-time Gaussian Splatting for Dynamic Endoscopic Scene ReconstructionCode0
Self-Supervised Learning based Depth Estimation from Monocular ImagesCode0
Dense Depth Estimation in Monocular Endoscopy with Self-supervised Learning MethodsCode0
Unified Depth Prediction and Intrinsic Image Decomposition from a Single Image via Joint Convolutional Neural FieldsCode0
Light Field Compression by Residual CNN Assisted JPEGCode0
Eliminating the Blind Spot: Adapting 3D Object Detection and Monocular Depth Estimation to 360° Panoramic ImageryCode0
Task-Agnostic Attacks Against Vision Foundation ModelsCode0
Show:102550
← PrevPage 47 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