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 451–500 of 2454 papers

TitleStatusHype
MonoJSG: Joint Semantic and Geometric Cost Volume for Monocular 3D Object DetectionCode1
Joint Learning of Salient Object Detection, Depth Estimation and Contour ExtractionCode1
Monocular Depth Distribution Alignment with Low ComputationCode1
ChiTransformer:Towards Reliable Stereo from CuesCode1
Lightweight Monocular Depth Estimation through Guided DecodingCode1
Pseudo-Stereo for Monocular 3D Object Detection in Autonomous DrivingCode1
Occlusion-Aware Cost Constructor for Light Field Depth EstimationCode1
MUAD: Multiple Uncertainties for Autonomous Driving, a benchmark for multiple uncertainty types and tasksCode1
OmniFusion: 360 Monocular Depth Estimation via Geometry-Aware FusionCode1
360 Depth Estimation in the Wild -- The Depth360 Dataset and the SegFuse NetworkCode1
Automated Distance Estimation for Wildlife Camera TrappingCode1
Transformers in Self-Supervised Monocular Depth Estimation with Unknown Camera IntrinsicsCode1
GLPanoDepth: Global-to-Local Panoramic Depth EstimationCode1
Mobile Robot Manipulation using Pure Object DetectionCode1
A Confidence-based Iterative Solver of Depths and Surface Normals for Deep Multi-view StereoCode1
Global-Local Path Networks for Monocular Depth Estimation with Vertical CutDepthCode1
Maximizing Self-supervision from Thermal Image for Effective Self-supervised Learning of Depth and Ego-motionCode1
Robust photon-efficient imaging using a pixel-wise residual shrinkage networkCode1
Stereo Depth From Events Cameras: Concentrate and Focus on the FutureCode1
Discrete Time Convolution for Fast Event-Based StereoCode1
Chitransformer: Towards Reliable Stereo From CuesCode1
Dense Depth Estimation from Multiple 360-degree Images Using Virtual DepthCode1
ACDNet: Adaptively Combined Dilated Convolution for Monocular Panorama Depth EstimationCode1
Channel-Wise Attention-Based Network for Self-Supervised Monocular Depth EstimationCode1
Towards General and Efficient Active LearningCode1
Multi-View Depth Estimation by Fusing Single-View Depth Probability with Multi-View GeometryCode1
Self-Supervised Monocular Depth and Ego-Motion Estimation in Endoscopy: Appearance Flow to the RescueCode1
GCNDepth: Self-supervised Monocular Depth Estimation based on Graph Convolutional NetworkCode1
Curvature-guided dynamic scale networks for Multi-view StereoCode1
PolyphonicFormer: Unified Query Learning for Depth-aware Video Panoptic SegmentationCode1
Toward Practical Monocular Indoor Depth EstimationCode1
Gated2Gated: Self-Supervised Depth Estimation from Gated ImagesCode1
Generalized Binary Search Network for Highly-Efficient Multi-View StereoCode1
SGM3D: Stereo Guided Monocular 3D Object DetectionCode1
Object-aware Monocular Depth Prediction with Instance ConvolutionsCode1
Efficient Neural Radiance Fields for Interactive Free-viewpoint VideoCode1
A benchmark with decomposed distribution shifts for 360 monocular depth estimationCode1
3DVNet: Multi-View Depth Prediction and Volumetric RefinementCode1
360MonoDepth: High-Resolution 360° Monocular Depth EstimationCode1
Instance-wise Occlusion and Depth Orders in Natural ScenesCode1
TriStereoNet: A Trinocular Framework for Multi-baseline Disparity EstimationCode1
MonoPLFlowNet: Permutohedral Lattice FlowNet for Real-Scale 3D Scene FlowEstimation with Monocular ImagesCode1
SUB-Depth: Self-distillation and Uncertainty Boosting Self-supervised Monocular Depth EstimationCode1
Absolute distance prediction based on deep learning object detection and monocular depth estimation modelsCode1
PlaneRecNet: Multi-Task Learning with Cross-Task Consistency for Piece-Wise Plane Detection and Reconstruction from a Single RGB ImageCode1
Self-Supervised Monocular Depth Estimation with Internal Feature FusionCode1
DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D QueriesCode1
PLNet: Plane and Line Priors for Unsupervised Indoor Depth EstimationCode1
Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D ScansCode1
Stereo Hybrid Event-Frame (SHEF) Cameras for 3D PerceptionCode1
Show:102550
← PrevPage 10 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