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 1801–1850 of 2454 papers

TitleStatusHype
A Hybrid mmWave and Camera System for Long-Range Depth Imaging—0
Deterministic Guided LiDAR Depth Map Completion—0
Predicting Depth from Semantic Segmentation using Game Engine Dataset—0
Instance-Level Task Parameters: A Robust Multi-task Weighting Framework—0
3D Semantic Mapping from Arthroscopy using Out-of-distribution Pose and Depth and In-distribution Segmentation Training—0
Self-supervised Depth Estimation Leveraging Global Perception and Geometric Smoothness Using On-board Videos—0
Occlusion-aware Unsupervised Learning of Depth from 4-D Light FieldsCode0
Self-Supervised Learning of Domain Invariant Features for Depth Estimation—0
Towards urban scenes understanding through polarization cues—0
Real-time Monocular Depth Estimation with Sparse Supervision on Mobile—0
Self-Guided Instance-Aware Network for Depth Completion and Enhancement—0
A Novel 3D-UNet Deep Learning Framework Based on High-Dimensional Bilateral Grid for Edge Consistent Single Image Depth Estimation—0
Fast and Accurate Single-Image Depth Estimation on Mobile Devices, Mobile AI 2021 Challenge: Report—0
Superevents: Towards Native Semantic Segmentation for Event-based Cameras—0
Moving SLAM: Fully Unsupervised Deep Learning in Non-Rigid Scenes—0
LAFFNet: A Lightweight Adaptive Feature Fusion Network for Underwater Image Enhancement—0
A Novel Binocular Eye-Tracking SystemWith Stereo Stimuli for 3D Gaze Estimation—0
Co-training for Deep Object Detection: Comparing Single-modal and Multi-modal Approaches—0
H-Net: Unsupervised Attention-based Stereo Depth Estimation Leveraging Epipolar Geometry—0
MonoGRNet: A General Framework for Monocular 3D Object Detection—0
Depth Completion using Plane-Residual Representation—0
Dynamic Fusion Network For Light Field Depth Estimation—0
Learning Multi-modal Information for Robust Light Field Depth EstimationCode0
Single Image Depth Estimation: An Overview—0
Exploring Geometric Consistency for Monocular 3D Object Detection—0
Domain Adaptive Monocular Depth Estimation With Semantic Information—0
Improving Online Performance Prediction for Semantic Segmentation—0
iELAS: An ELAS-Based Energy-Efficient Accelerator for Real-Time Stereo Matching on FPGA Platform—0
Stereo Matching by Self-supervision of Multiscopic Vision—0
SVDistNet: Self-Supervised Near-Field Distance Estimation on Surround View Fisheye Cameras—0
Deep Monocular 3D Human Pose Estimation via Cascaded Dimension-Lifting—0
Instantaneous Stereo Depth Estimation of Real-World Stimuli with a Neuromorphic Stereo-Vision Setup—0
A Front-End for Dense Monocular SLAM using a Learned Outlier Mask Prior—0
Improved and efficient inter-vehicle distance estimation using road gradients of both ego and target vehicles—0
Unpaired Single-Image Depth Synthesis with cycle-consistent Wasserstein GANs—0
Geometric Unsupervised Domain Adaptation for Semantic Segmentation—0
DynOcc: Learning Single-View Depth from Dynamic Occlusion Cues—0
Bayesian Deep Basis Fitting for Depth Completion with Uncertainty—0
Generalizing to the Open World: Deep Visual Odometry with Online Adaptation—0
Factors of Influence for Transfer Learning across Diverse Appearance Domains and Task Types—0
Volumetric Propagation Network: Stereo-LiDAR Fusion for Long-Range Depth Estimation—0
Learning Scene Structure Guidance via Cross-Task Knowledge Transfer for Single Depth Super-Resolution—0
A Framework for 3D Tracking of Frontal Dynamic Objects in Autonomous Cars—0
SaccadeCam: Adaptive Visual Attention for Monocular Depth SensingCode0
Revisiting Self-Supervised Monocular Depth EstimationCode0
Stereo Object Matching Network—0
Unsupervised Learning of Depth Estimation and Visual Odometry for Sparse Light Field Cameras—0
Stereo CenterNet based 3D Object Detection for Autonomous Driving—0
Bootstrapped Self-Supervised Training with Monocular Video for Semantic Segmentation and Depth Estimation—0
Generic Perceptual Loss for Modeling Structured Output Dependencies—0
Show:102550
← PrevPage 37 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