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 1451–1500 of 2454 papers

TitleStatusHype
Spectral 3D Computer Vision -- A Review—0
EVEN: An Event-Based Framework for Monocular Depth Estimation at Adverse Night Conditions—0
A Systematic Performance Analysis of Deep Perceptual Loss Networks: Breaking Transfer Learning ConventionsCode0
A Disparity Refinement Framework for Learning-based Stereo Matching Methods in Cross-domain Setting for Laparoscopic Images—0
Multi-Task Self-Supervised Learning for Image Segmentation Task—0
SceneScape: Text-Driven Consistent Scene Generation—0
Uncertainty-Driven Dense Two-View Structure from Motion—0
Recurrent Structure Attention Guidance for Depth Super-Resolution—0
Structure Flow-Guided Network for Real Depth Super-Resolution—0
Leveraging the Third Dimension in Contrastive Learning—0
HDPV-SLAM: Hybrid Depth-augmented Panoramic Visual SLAM for Mobile Mapping System with Tilted LiDAR and Panoramic Visual Camera—0
Learning Good Features to Transfer Across Tasks and Domains—0
FG-Depth: Flow-Guided Unsupervised Monocular Depth Estimation—0
Unsupervised Light Field Depth Estimation via Multi-view Feature Matching with Occlusion Prediction—0
SoftEnNet: Symbiotic Monocular Depth Estimation and Lumen Segmentation for Colonoscopy Endorobots—0
Booster: a Benchmark for Depth from Images of Specular and Transparent Surfaces—0
S^2Net: Accurate Panorama Depth Estimation on Spherical Surface—0
Dyna-DepthFormer: Multi-frame Transformer for Self-Supervised Depth Estimation in Dynamic Scenes—0
Deep Planar Parallax for Monocular Depth Estimation—0
DepthP+P: Metric Accurate Monocular Depth Estimation using Planar and Parallax—0
BS3D: Building-scale 3D Reconstruction from RGB-D Images—0
Deep Depth Estimation From Thermal ImageCode0
Multi-Task Learning with Knowledge Distillation for Dense Prediction—0
Omnimatte3D: Associating Objects and Their Effects in Unconstrained Monocular Video—0
Depth Estimation From Camera Image and mmWave Radar Point Cloud—0
Consistent Depth Prediction for Transparent Object Reconstruction from RGB-D Camera—0
Semantic Information in Contrastive LearningCode0
Guiding Local Feature Matching with Surface Curvature—0
NeuralLift-360: Lifting an In-the-Wild 2D Photo to a 3D Object With 360deg Views—0
Semi-Supervised Stereo-Based 3D Object Detection via Cross-View Consensus—0
SlaBins: Fisheye Depth Estimation using Slanted Bins on Road Environments—0
CORE: Co-planarity Regularized Monocular Geometry Estimation with Weak Supervision—0
HRDFuse: Monocular 360deg Depth Estimation by Collaboratively Learning Holistic-With-Regional Depth Distributions—0
3D Distillation: Improving Self-Supervised Monocular Depth Estimation on Reflective Surfaces—0
DPS-Net: Deep Polarimetric Stereo Depth Estimation—0
Achievement-Based Training Progress Balancing for Multi-Task LearningCode0
ObjectFusion: Multi-modal 3D Object Detection with Object-Centric Fusion—0
Spatio-Focal Bidirectional Disparity Estimation From a Dual-Pixel Image—0
Multi-body Depth and Camera Pose Estimation from Multiple ViewsCode0
AttEntropy: On the Generalization Ability of Supervised Semantic Segmentation Transformers to New Objects in New DomainsCode0
HandsOff: Labeled Dataset Generation With No Additional Human Annotations—0
Vision-Based Environmental Perception for Autonomous Driving—0
Shakes on a Plane: Unsupervised Depth Estimation from Unstabilized Photography—0
Depth Estimation maps of lidar and stereo images—0
Lightweight Monocular Depth Estimation—0
Solve the Puzzle of Instance Segmentation in Videos: A Weakly Supervised Framework with Spatio-Temporal Collaboration—0
ROIFormer: Semantic-Aware Region of Interest Transformer for Efficient Self-Supervised Monocular Depth Estimation—0
Cross-Domain Synthetic-to-Real In-the-Wild Depth and Normal Estimation for 3D Scene Understanding—0
Objects as Spatio-Temporal 2.5D points—0
Event-based Monocular Dense Depth Estimation with Recurrent Transformers—0
Show:102550
← PrevPage 30 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