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 2351–2400 of 2454 papers

TitleStatusHype
Low Compute and Fully Parallel Computer Vision With HashMatch—0
J-MOD^2: Joint Monocular Obstacle Detection and Depth Estimation—0
Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single ImageCode0
Estimated Depth Map Helps Image ClassificationCode0
Exact Blur Measure Outperforms Conventional Learned Features for Depth Finding—0
A Compromise Principle in Deep Monocular Depth Estimation—0
Automatic Discovery and Geotagging of Objects from Street View ImageryCode0
Multi-task Self-Supervised Visual Learning—0
Sparsity Invariant CNNsCode0
Reflection Separation and Deblurring of Plenoptic Images—0
Learning to Synthesize a 4D RGBD Light Field from a Single ImageCode0
SPLODE: Semi-Probabilistic Point and Line Odometry with Depth Estimation from RGB-D Camera Motion—0
Fast Scene Understanding for Autonomous DrivingCode0
Accurate Light Field Depth Estimation with Superpixel Regularization over Partially Occluded Regions—0
Monocular Depth Estimation with Hierarchical Fusion of Dilated CNNs and Soft-Weighted-Sum InferenceCode0
Occlusion Handling using Semantic Segmentation and Visibility-Based Rendering for Mixed Reality—0
The Devil is in the Decoder: Classification, Regression and GANsCode0
Spatial and Angular Resolution Enhancement of Light Fields Using Convolutional Neural Networks—0
A Wide-Field-Of-View Monocentric Light Field Camera—0
Recurrent Scene Parsing with Perspective Understanding in the LoopCode0
Self-Supervised Siamese Learning on Stereo Image Pairs for Depth Estimation in Robotic Surgery—0
Out-of-focus: Learning Depth from Image Bokeh for Robotic Perception—0
Single image depth estimation by dilated deep residual convolutional neural network and soft-weight-sum inferenceCode0
Unsupervised Learning of Depth and Ego-Motion from VideoCode0
OCRAPOSE II: An OCR-based indoor positioning system using mobile phone images—0
CNN-SLAM: Real-time dense monocular SLAM with learned depth predictionCode0
Surface Normals in the Wild—0
Multi-Scale Continuous CRFs as Sequential Deep Networks for Monocular Depth EstimationCode0
SeGAN: Segmenting and Generating the InvisibleCode0
Depth from Monocular Images using a Semi-Parallel Deep Neural Network (SPDNN) Hybrid Architecture—0
Sparse Depth Sensing for Resource-Constrained RobotsCode0
Depth Estimation using Modified Cost Function for Occlusion Handling—0
Analyzing Modular CNN Architectures for Joint Depth Prediction and Semantic Segmentation—0
Computing Egomotion with Local Loop Closures for Egocentric Videos—0
Light Field Super-Resolution Via Graph-Based Regularization—0
SceneNet RGB-D: 5M Photorealistic Images of Synthetic Indoor Trajectories with Ground TruthCode0
Single-View and Multi-View Depth Fusion—0
Hybrid Light Field Imaging for Improved Spatial Resolution and Depth Range—0
Light Field Stitching for Extended Synthetic Aperture—0
CAD2RL: Real Single-Image Flight without a Single Real ImageCode0
Learning to Navigate in Complex EnvironmentsCode0
Parse Geometry from a Line: Monocular Depth Estimation with Partial Laser ObservationCode0
ResearchDoom and CocoDoom: Learning Computer Vision with Games—0
Exploiting Depth from Single Monocular Images for Object Detection and Semantic Segmentation—0
Two-stage Convolutional Part Heatmap Regression for the 1st 3D Face Alignment in the Wild (3DFAW) ChallengeCode0
Geometry-Based Next Frame Prediction from Monocular Video—0
Depth Estimation Through a Generative Model of Light Field Synthesis—0
Occlusion-Model Guided Anti-Occlusion Depth Estimation in Light Field—0
Play and Learn: Using Video Games to Train Computer Vision Models—0
Fast Robust Monocular Depth Estimation for Obstacle Detection with Fully Convolutional NetworksCode0
Show:102550
← PrevPage 48 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