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 251–300 of 2454 papers

TitleStatusHype
Camera-based 3D Semantic Scene Completion with Sparse Guidance NetworkCode1
Fully Convolutional Slice-to-Volume Reconstruction for Single-Stack MRICode1
BEVNeXt: Reviving Dense BEV Frameworks for 3D Object DetectionCode1
GIVT: Generative Infinite-Vocabulary TransformersCode1
Deeper into Self-Supervised Monocular Indoor Depth EstimationCode1
Sparse Beats Dense: Rethinking Supervision in Radar-Camera Depth CompletionCode1
Transferring to Real-World Layouts: A Depth-aware Framework for Scene AdaptationCode1
RENI++ A Rotation-Equivariant, Scale-Invariant, Natural Illumination PriorCode1
NDDepth: Normal-Distance Assisted Monocular Depth Estimation and CompletionCode1
MonoDiffusion: Self-Supervised Monocular Depth Estimation Using Diffusion ModelCode1
MonoProb: Self-Supervised Monocular Depth Estimation with Interpretable UncertaintyCode1
TSP-Transformer: Task-Specific Prompts Boosted Transformer for Holistic Scene UnderstandingCode1
Bridging the Gap between Multi-focus and Multi-modal: A Focused Integration Framework for Multi-modal Image FusionCode1
Metrically Scaled Monocular Depth Estimation through Sparse Priors for Underwater RobotsCode1
G2-MonoDepth: A General Framework of Generalized Depth Inference from Monocular RGB+X DataCode1
Mobile AR Depth Estimation: Challenges & Prospects -- Extended VersionCode1
ConsistNet: Enforcing 3D Consistency for Multi-view Images DiffusionCode1
EC-Depth: Exploring the consistency of self-supervised monocular depth estimation in challenging scenesCode1
WeatherDepth: Curriculum Contrastive Learning for Self-Supervised Depth Estimation under Adverse Weather ConditionsCode1
Multi-task Learning with 3D-Aware RegularizationCode1
Text-image Alignment for Diffusion-based PerceptionCode1
Finite Scalar Quantization: VQ-VAE Made SimpleCode1
GasMono: Geometry-Aided Self-Supervised Monocular Depth Estimation for Indoor ScenesCode1
IEBins: Iterative Elastic Bins for Monocular Depth EstimationCode1
InSpaceType: Reconsider Space Type in Indoor Monocular Depth EstimationCode1
NDDepth: Normal-Distance Assisted Monocular Depth EstimationCode1
GEDepth: Ground Embedding for Monocular Depth EstimationCode1
X-PDNet: Accurate Joint Plane Instance Segmentation and Monocular Depth Estimation with Cross-Task Distillation and Boundary CorrectionCode1
Towards Better Data Exploitation in Self-Supervised Monocular Depth EstimationCode1
Bayes' Rays: Uncertainty Quantification for Neural Radiance FieldsCode1
Two-in-One Depth: Bridging the Gap Between Monocular and Binocular Self-supervised Depth EstimationCode1
SQLdepth: Generalizable Self-Supervised Fine-Structured Monocular Depth EstimationCode1
Learning to Upsample by Learning to SampleCode1
Calibrating Panoramic Depth Estimation for Practical Localization and MappingCode1
ARAI-MVSNet: A multi-view stereo depth estimation network with adaptive depth range and depth intervalCode1
DS-Depth: Dynamic and Static Depth Estimation via a Fusion Cost VolumeCode1
Out-of-Distribution Detection for Monocular Depth EstimationCode1
Self-Supervised Monocular Depth Estimation by Direction-aware Cumulative Convolution NetworkCode1
Blur aware metric depth estimation with multi-focus plenoptic camerasCode1
Digging Into Uncertainty-based Pseudo-label for Robust Stereo MatchingCode1
Learning Depth Estimation for Transparent and Mirror SurfacesCode1
Towards Deeply Unified Depth-aware Panoptic Segmentation with Bi-directional Guidance LearningCode1
PlaneRecTR++: Unified Query Learning for Joint 3D Planar Reconstruction and Pose EstimationCode1
LiDAR Meta Depth CompletionCode1
FDCT: Fast Depth Completion for Transparent ObjectsCode1
SimCol3D -- 3D Reconstruction during Colonoscopy ChallengeCode1
Kick Back & Relax: Learning to Reconstruct the World by Watching SlowTVCode1
Constraining Depth Map Geometry for Multi-View Stereo: A Dual-Depth Approach with Saddle-shaped Depth CellsCode1
Self-supervised Monocular Depth Estimation: Let's Talk About The WeatherCode1
On Point Affiliation in Feature UpsamplingCode1
Show:102550
← PrevPage 6 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