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

Showing 24012450 of 2454 papers

TitleStatusHype
Robust Light Field Depth Estimation for Noisy Scene With Occlusion0
Simultaneous Estimation of Near IR BRDF and Fine-Scale Surface Geometry0
Dense Monocular Depth Estimation in Complex Dynamic Scenes0
Structured Regression Gradient Boosting0
Macroscopic Interferometry: Rethinking Depth Estimation With Frequency-Domain Time-Of-Flight0
Heterogeneous Light Fields0
Stereo Matching With Color and Monochrome Cameras in Low-Light Conditions0
Panoramic Stereo Videos With a Single Camera0
What Sparse Light Field Coding Reveals About Scene Structure0
Monocular Depth Estimation Using Neural Regression Forest0
Deeper Depth Prediction with Fully Convolutional Residual NetworksCode1
Dynamic Filter NetworksCode0
Depth from a Single Image by Harmonizing Overcomplete Local Network Predictions0
Estimating Depth from Monocular Images as Classification Using Deep Fully Convolutional Residual Networks0
Joint Semantic Segmentation and Depth Estimation with Deep Convolutional Networks0
Symmetry-aware Depth Estimation using Deep Neural Networks0
Deep3D: Fully Automatic 2D-to-3D Video Conversion with Deep Convolutional Neural NetworksCode2
Single-Image Depth Perception in the WildCode0
Waterdrop Stereo0
Unified Depth Prediction and Intrinsic Image Decomposition from a Single Image via Joint Convolutional Neural FieldsCode0
Unsupervised CNN for Single View Depth Estimation: Geometry to the RescueCode0
Image and Depth from a Single Defocused Image Using Coded Aperture Photography0
Discriminative Training of Deep Fully-connected Continuous CRF with Task-specific Loss0
Occlusion-Aware Depth Estimation Using Light-Field Cameras0
Intrinsic Depth: Improving Depth Transfer With Intrinsic Images0
Learning Ordinal Relationships for Mid-Level Vision0
Direct, Dense, and Deformable: Template-Based Non-Rigid 3D Reconstruction From RGB Video0
High Quality Structure From Small Motion for Rolling Shutter Cameras0
Structured Depth Prediction in Challenging Monocular Video Sequences0
Depth Extraction from Videos Using Geometric Context and Occlusion Boundaries0
Lifting GIS Maps into Strong Geometric Context for Scene Understanding0
HC-Search for Structured Prediction in Computer Vision0
Depth From Shading, Defocus, and Correspondence Using Light-Field Angular Coherence0
Towards Unified Depth and Semantic Prediction From a Single Image0
Indoor Scene Structure Analysis for Single Image Depth Estimation0
Superpixel Meshes for Fast Edge-Preserving Surface Reconstruction0
Direction Matters: Depth Estimation With a Surface Normal Classifier0
Accurate Depth Map Estimation From a Lenslet Light Field Camera0
Diffusion Methods for Classification with Pairwise Relationships0
Learning Depth from Single Monocular Images Using Deep Convolutional Neural FieldsCode0
Coupled Depth Learning0
Analog Signal Processing Approach for Coarse and Fine Depth Estimation0
Vision and Learning for Deliberative Monocular Cluttered Flight0
Deep Convolutional Neural Fields for Depth Estimation from a Single Image0
Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional ArchitectureCode0
Joint Depth Estimation and Camera Shake Removal from Single Blurry Image0
Pulling Things out of Perspective0
Discrete-Continuous Depth Estimation from a Single Image0
Bayesian Depth-from-Defocus with Shading Constraints0
Single View Depth Estimation from Examples0
Show:102550
← PrevPage 49 of 50Next →

Benchmark Results

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