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 301–350 of 2454 papers

TitleStatusHype
EvGGS: A Collaborative Learning Framework for Event-based Generalizable Gaussian SplattingCode1
A Study on Self-Supervised Pretraining for Vision Problems in Gastrointestinal EndoscopyCode1
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text AlignmentCode1
EPI-based Oriented Relation Networks for Light Field Depth EstimationCode1
Energy-Efficient Adaptive 3D SensingCode1
ES-Net: An Efficient Stereo Matching NetworkCode1
Excavating the Potential Capacity of Self-Supervised Monocular Depth EstimationCode1
EndoMUST: Monocular Depth Estimation for Robotic Endoscopy via End-to-end Multi-step Self-supervised TrainingCode1
EndoDepth: A Benchmark for Assessing Robustness in Endoscopic Depth PredictionCode1
EndoOmni: Zero-Shot Cross-Dataset Depth Estimation in Endoscopy by Robust Self-Learning from Noisy LabelsCode1
DAG: Depth-Aware Guidance with Denoising Diffusion Probabilistic ModelsCode1
3DVNet: Multi-View Depth Prediction and Volumetric RefinementCode1
Collaboration Helps Camera Overtake LiDAR in 3D DetectionCode1
DenseMTL: Cross-task Attention Mechanism for Dense Multi-task LearningCode1
End-to-End Pseudo-LiDAR for Image-Based 3D Object DetectionCode1
Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuningCode1
Generalizable Data-free Objective for Crafting Universal Adversarial PerturbationsCode1
EC-Depth: Exploring the consistency of self-supervised monocular depth estimation in challenging scenesCode1
Adaptive Surface Normal Constraint for Depth EstimationCode1
Dyna-DM: Dynamic Object-aware Self-supervised Monocular Depth MapsCode1
Are We Ready for Vision-Centric Driving Streaming Perception? The ASAP BenchmarkCode1
Combining Events and Frames using Recurrent Asynchronous Multimodal Networks for Monocular Depth PredictionCode1
ARAI-MVSNet: A multi-view stereo depth estimation network with adaptive depth range and depth intervalCode1
Edge-aware Bidirectional Diffusion for Dense Depth Estimation from Light FieldsCode1
360MonoDepth: High-Resolution 360° Monocular Depth EstimationCode1
CoDEPS: Online Continual Learning for Depth Estimation and Panoptic SegmentationCode1
4K-HAZE: A Dehazing Benchmark with 4K Resolution Hazy and Haze-Free ImagesCode1
CT-MVSNet: Efficient Multi-View Stereo with Cross-scale TransformerCode1
3D Visual Illusion Depth EstimationCode1
ENRICH: Multi-purposE dataset for beNchmaRking In Computer vision and pHotogrammetryCode1
Dusk Till Dawn: Self-supervised Nighttime Stereo Depth Estimation using Visual Foundation ModelsCode1
Estimating Image Depth in the Comics DomainCode1
A Study on the Generality of Neural Network Structures for Monocular Depth EstimationCode1
Event-based Stereo Depth Estimation from Ego-motion using Ray Density FusionCode1
Dual Transfer Learning for Event-based End-task Prediction via Pluggable Event to Image TranslationCode1
Curvature-guided dynamic scale networks for Multi-view StereoCode1
A Practical Stereo Depth System for Smart GlassesCode1
Exploring Sparse Visual Prompt for Domain Adaptive Dense PredictionCode1
Edge-Enabled VIO with Long-Tracked Features for High-Accuracy Low-Altitude IoT NavigationCode1
CL-MVSNet: Unsupervised Multi-View Stereo with Dual-Level Contrastive LearningCode1
DS-Depth: Dynamic and Static Depth Estimation via a Fusion Cost VolumeCode1
ConsistNet: Enforcing 3D Consistency for Multi-view Images DiffusionCode1
DORT: Modeling Dynamic Objects in Recurrent for Multi-Camera 3D Object Detection and TrackingCode1
Advancing Self-supervised Monocular Depth Learning with Sparse LiDARCode1
Context-Enhanced Stereo TransformerCode1
Continual Adaptation for Deep StereoCode1
Dual Pixel Exploration: Simultaneous Depth Estimation and Image RestorationCode1
A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth ImageCode1
DiverseDepth: Affine-invariant Depth Prediction Using Diverse DataCode1
Does it work outside this benchmark? Introducing the Rigid Depth Constructor tool, depth validation dataset construction in rigid scenes for the massesCode1
Show:102550
← PrevPage 7 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