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 501–550 of 2454 papers

TitleStatusHype
Estimating Image Depth in the Comics DomainCode1
StereoSpike: Depth Learning with a Spiking Neural NetworkCode1
Excavating the Potential Capacity of Self-Supervised Monocular Depth EstimationCode1
Improving 360 Monocular Depth Estimation via Non-local Dense Prediction Transformer and Joint Supervised and Self-supervised LearningCode1
Advancing Self-supervised Monocular Depth Learning with Sparse LiDARCode1
RVMDE: Radar Validated Monocular Depth Estimation for RoboticsCode1
LiDARTouch: Monocular metric depth estimation with a few-beam LiDARCode1
Pano3D: A Holistic Benchmark and a Solid Baseline for 360^o Depth EstimationCode1
Dual Transfer Learning for Event-based End-task Prediction via Pluggable Event to Image TranslationCode1
NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view StereoCode1
Improving Semi-Supervised and Domain-Adaptive Semantic Segmentation with Self-Supervised Depth EstimationCode1
Real-Time Monocular Human Depth Estimation and Segmentation on Embedded SystemsCode1
Bridging Unsupervised and Supervised Depth from Focus via All-in-Focus SupervisionCode1
MobileStereoNet: Towards Lightweight Deep Networks for Stereo MatchingCode1
StructDepth: Leveraging the structural regularities for self-supervised indoor depth estimationCode1
Fine-grained Semantics-aware Representation Enhancement for Self-supervised Monocular Depth EstimationCode1
A Hybrid Sparse-Dense Monocular SLAM System for Autonomous DrivingCode1
Self-supervised Monocular Depth Estimation for All Day Images using Domain SeparationCode1
Is Pseudo-Lidar needed for Monocular 3D Object detection?Code1
Multi-Source Fusion and Automatic Predictor Selection for Zero-Shot Video Object SegmentationCode1
Improving Single-Image Defocus Deblurring: How Dual-Pixel Images Help Through Multi-Task LearningCode1
Towards Interpretable Deep Networks for Monocular Depth EstimationCode1
Regularizing Nighttime Weirdness: Efficient Self-supervised Monocular Depth Estimation in the DarkCode1
Bird's-Eye-View Panoptic Segmentation Using Monocular Frontal View ImagesCode1
Geometry Uncertainty Projection Network for Monocular 3D Object DetectionCode1
Learning Geometry-Guided Depth via Projective Modeling for Monocular 3D Object DetectionCode1
Unsupervised Monocular Depth Estimation in Highly Complex EnvironmentsCode1
Photon-Starved Scene Inference using Single Photon CamerasCode1
CutDepth:Edge-aware Data Augmentation in Depth EstimationCode1
Depth Estimation from Monocular Images and Sparse radar using Deep Ordinal Regression NetworkCode1
Edge-aware Bidirectional Diffusion for Dense Depth Estimation from Light FieldsCode1
TransformerFusion: Monocular RGB Scene Reconstruction using TransformersCode1
E-DSSR: Efficient Dynamic Surgical Scene Reconstruction with Transformer-based Stereoscopic Depth PerceptionCode1
Self-Supervised Monocular Depth Estimation of Untextured Indoor Rotated ScenesCode1
Differentiable Diffusion for Dense Depth Estimation from Multi-view ImagesCode1
Self-Supervised Learning with Kernel Dependence MaximizationCode1
Mirror3D: Depth Refinement for Mirror SurfacesCode1
Single Image Depth Prediction with Wavelet DecompositionCode1
Deep Color Mismatch Correction In Stereoscopic 3D ImagesCode1
Unsupervised Joint Learning of Depth, Optical Flow, Ego-motion from VideoCode1
Unsupervised Scale-consistent Depth Learning from VideoCode1
SBEVNet: End-to-End Deep Stereo Layout EstimationCode1
M4Depth: Monocular depth estimation for autonomous vehicles in unseen environmentsCode1
Learning to Relate Depth and Semantics for Unsupervised Domain AdaptationCode1
Boosting Light-Weight Depth Estimation Via Knowledge DistillationCode1
Deep Multi-View Stereo gone wildCode1
The Temporal Opportunist: Self-Supervised Multi-Frame Monocular DepthCode1
Domain Adaptive Semantic Segmentation with Self-Supervised Depth EstimationCode1
2.5D Visual Relationship DetectionCode1
UnrealROX+: An Improved Tool for Acquiring Synthetic Data from Virtual 3D EnvironmentsCode1
Show:102550
← PrevPage 11 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