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
On Point Affiliation in Feature UpsamplingCode1
FlipNeRF: Flipped Reflection Rays for Few-shot Novel View SynthesisCode1
MIMIC: Masked Image Modeling with Image CorrespondencesCode1
Learnable Differencing Center for Nighttime Depth PerceptionCode1
Cross-modal transformers for infrared and visible image fusionCode1
Depth and DOF Cues Make A Better Defocus Blur DetectorCode1
Tame a Wild Camera: In-the-Wild Monocular Camera CalibrationCode1
Predict to Detect: Prediction-guided 3D Object Detection using Sequential ImagesCode1
SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-DepthCode1
Towards In-context Scene UnderstandingCode1
A technique to jointly estimate depth and depth uncertainty for unmanned aerial vehiclesCode1
DaRF: Boosting Radiance Fields from Sparse Inputs with Monocular Depth AdaptationCode1
OccCasNet: Occlusion-aware Cascade Cost Volume for Light Field Depth EstimationCode1
Text2NeRF: Text-Driven 3D Scene Generation with Neural Radiance FieldsCode1
Brain Captioning: Decoding human brain activity into images and textCode1
Virtual Occlusions Through Implicit DepthCode1
ViP-NeRF: Visibility Prior for Sparse Input Neural Radiance FieldsCode1
RGB-D Indiscernible Object Counting in Underwater ScenesCode1
A geometry-aware deep network for depth estimation in monocular endoscopyCode1
Learning to Fuse Monocular and Multi-view Cues for Multi-frame Depth Estimation in Dynamic ScenesCode1
Temporally Consistent Online Depth Estimation Using Point-Based FusionCode1
DualRefine: Self-Supervised Depth and Pose Estimation Through Iterative Epipolar Sampling and Refinement Toward EquilibriumCode1
DEFLOW: Self-supervised 3D Motion Estimation of Debris FlowCode1
altiro3D: Scene representation from single image and novel view synthesisCode1
ENRICH: Multi-purposE dataset for beNchmaRking In Computer vision and pHotogrammetryCode1
DORT: Modeling Dynamic Objects in Recurrent for Multi-Camera 3D Object Detection and TrackingCode1
An intelligent modular real-time vision-based system for environment perceptionCode1
4K-HAZE: A Dehazing Benchmark with 4K Resolution Hazy and Haze-Free ImagesCode1
On the Importance of Accurate Geometry Data for Dense 3D Vision TasksCode1
Collaboration Helps Camera Overtake LiDAR in 3D DetectionCode1
Monocular Visual-Inertial Depth EstimationCode1
Fully Self-Supervised Depth Estimation from Defocus ClueCode1
Channel-Aware Distillation Transformer for Depth Estimation on Nano DronesCode1
CoDEPS: Online Continual Learning for Depth Estimation and Panoptic SegmentationCode1
Exploring Sparse Visual Prompt for Domain Adaptive Dense PredictionCode1
Lifelong-MonoDepth: Lifelong Learning for Multi-Domain Monocular Metric Depth EstimationCode1
RM-Depth: Unsupervised Learning of Recurrent Monocular Depth in Dynamic ScenesCode1
Aberration-Aware Depth-from-FocusCode1
SUPS: A Simulated Underground Parking Scenario Dataset for Autonomous DrivingCode1
FLSea: Underwater Visual-Inertial and Stereo-Vision Forward-Looking DatasetsCode1
MixNeRF: Modeling a Ray with Mixture Density for Novel View Synthesis from Sparse InputsCode1
URCDC-Depth: Uncertainty Rectified Cross-Distillation with CutFlip for Monocular Depth EstimationCode1
VA-DepthNet: A Variational Approach to Single Image Depth PredictionCode1
STEPS: Joint Self-supervised Nighttime Image Enhancement and Depth EstimationCode1
Adversarial Training of Self-supervised Monocular Depth Estimation against Physical-World AttacksCode1
AudioEar: Single-View Ear Reconstruction for Personalized Spatial AudioCode1
On the Adversarial Robustness of Camera-based 3D Object DetectionCode1
Improving Deep Regression with Ordinal EntropyCode1
SwinDepth: Unsupervised Depth Estimation using Monocular Sequences via Swin Transformer and Densely Cascaded NetworkCode1
A Study on the Generality of Neural Network Structures for Monocular Depth EstimationCode1
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