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

Showing 17011750 of 2454 papers

TitleStatusHype
Scale-aware direct monocular odometry0
Scale Recovery for Monocular Visual Odometry Using Depth Estimated With Deep Convolutional Neural Fields0
Scaling 4D Representations0
Scaling Properties of Diffusion Models for Perceptual Tasks0
Scene Depth Estimation from Traditional Oriental Landscape Paintings0
SceneFactory: A Workflow-centric and Unified Framework for Incremental Scene Modeling0
SceneScape: Text-Driven Consistent Scene Generation0
SDC-Depth: Semantic Divide-and-Conquer Network for Monocular Depth Estimation0
SDGE: Stereo Guided Depth Estimation for 360^ Camera Sets0
SDL-MVS: View Space and Depth Deformable Learning Paradigm for Multi-View Stereo Reconstruction in Remote Sensing0
SDNet: Semantically Guided Depth Estimation Network0
SE(3) Equivariant Ray Embeddings for Implicit Multi-View Depth Estimation0
Seamless Augmented Reality Integration in Arthroscopy: A Pipeline for Articular Reconstruction and Guidance0
Seeing and Seeing Through the Glass: Real and Synthetic Data for Multi-Layer Depth Estimation0
See Yourself in Others: Attending Multiple Tasks for Own Failure Detection0
Segmentation-aware Prior Assisted Joint Global Information Aggregated 3D Building Reconstruction0
Selective Feature Adapter for Dense Vision Transformers0
Self-Attention Dense Depth Estimation Network for Unrectified Video Sequences0
Self-Guided Instance-Aware Network for Depth Completion and Enhancement0
Self-supervised 3D Object Detection from Monocular Pseudo-LiDAR0
Self-Supervised Attention Learning for Depth and Ego-motion Estimation0
Self-Supervised Camera Self-Calibration from Video0
Self-supervised Depth Estimation Leveraging Global Perception and Geometric Smoothness Using On-board Videos0
Self-supervised Depth Estimation to Regularise Semantic Segmentation in Knee Arthroscopy0
Self-Supervised Depth Estimation with Isometric-Self-Sample-Based Learning0
Self-supervised Event-based Monocular Depth Estimation using Cross-modal Consistency0
Self-Supervised Generative Adversarial Network for Depth Estimation in Laparoscopic Images0
Self-Supervised Joint Learning Framework of Depth Estimation via Implicit Cues0
Self-supervised Learning for Dense Depth Estimation in Monocular Endoscopy0
Self-Supervised Learning for Robotic Leaf Manipulation: A Hybrid Geometric-Neural Approach0
Self-supervised Learning for Single View Depth and Surface Normal Estimation0
Self-Supervised Learning of Depth and Camera Motion from 360° Videos0
Self-Supervised Learning of Domain Invariant Features for Depth Estimation0
Self-Supervised Light Field Depth Estimation Using Epipolar Plane Images0
Self-supervised Monocular Depth Estimation with Large Kernel Attention0
Self-supervised Monocular Depth Estimation Robust to Reflective Surface Leveraged by Triplet Mining0
Self-Supervised Monocular Depth Estimation in the Dark: Towards Data Distribution Compensation0
Self-supervised Monocular Depth Estimation on Water Scenes via Specular Reflection Prior0
Self-Supervised Monocular Depth Underwater0
Self-Supervised Monocular Image Depth Learning and Confidence Estimation0
Self-Supervised Monocular Scene Decomposition and Depth Estimation0
Self-supervised Multi-task Learning Framework for Safety and Health-Oriented Connected Driving Environment Perception using Onboard Camera0
Self-supervised Object Motion and Depth Estimation from Video0
Self-supervised Pretraining and Finetuning for Monocular Depth and Visual Odometry0
Self-Supervised Pre-training of Vision Transformers for Dense Prediction Tasks0
Self-Supervised Relative Depth Learning for Urban Scene Understanding0
Self-Supervised Siamese Learning on Stereo Image Pairs for Depth Estimation in Robotic Surgery0
Self-Supervised Spatially Variant PSF Estimation for Aberration-Aware Depth-from-Defocus0
SelfTune: Metrically Scaled Monocular Depth Estimation through Self-Supervised Learning0
SelfVIO: Self-Supervised Deep Monocular Visual-Inertial Odometry and Depth Estimation0
Show:102550
← PrevPage 35 of 50Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1OmniDepthRMSE0.62Unverified
2SphereDepthRMSE0.45Unverified
3Jin et al.RMSE0.42Unverified
4BiFuse with fusionRMSE0.41Unverified
5HoHoNet (ResNet-101)RMSE0.38Unverified
6PanoDepthRMSE0.37Unverified
7BiFuse++RMSE0.37Unverified
8UniFuse with fusionRMSE0.37Unverified
9DisConvRMSE0.37Unverified
10SliceNetRMSE0.37Unverified
#ModelMetricClaimedVerifiedStatus
1A2JmAP8.61Unverified
2PAD-NetRMS0.79Unverified
3MS-CRFRMS0.59Unverified
4DORNRMS0.51Unverified
5FreeformRMS0.43Unverified
6Optimized, freeformRMS0.43Unverified
7VNLRMS0.42Unverified
8BTSRMS0.41Unverified
9TransDepth (AGD+ ViT)RMS0.37Unverified
10AdaBinsRMS0.36Unverified
#ModelMetricClaimedVerifiedStatus
1T2NetAbs Rel0.35Unverified
2MIDASAbs Rel0.31Unverified
3Bhattacharjee et al.Abs Rel0.25Unverified
#ModelMetricClaimedVerifiedStatus
1T2NetAbs Rel0.49Unverified
2MIDASAbs Rel0.42Unverified
3Bhattacharjee et al.Abs Rel0.38Unverified
#ModelMetricClaimedVerifiedStatus
1LeReSabsolute relative error0.1Unverified
2DELTASabsolute relative error0.09Unverified
3Distill Any Depthabsolute relative error0.04Unverified
#ModelMetricClaimedVerifiedStatus
1SDC-DepthRMSE6.92Unverified
2SwinMTLRMSE6.35Unverified
#ModelMetricClaimedVerifiedStatus
1AIP-BrownDelta < 1.250.36Unverified
2LeResDelta < 1.250.23Unverified
#ModelMetricClaimedVerifiedStatus
1H-Net (Ours)Absolute relative error (AbsRel)0.09Unverified
2H-Net (Ours) Full EigenAbsolute relative error (AbsRel)0.08Unverified
#ModelMetricClaimedVerifiedStatus
1GLPDepthDelta < 1.250.43Unverified
2SRDINET (Model A)Delta < 1.250.4Unverified
#ModelMetricClaimedVerifiedStatus
1Atlas (finetuned)RMSE0.17Unverified
2Atlas (plain)RMSE0.17Unverified
#ModelMetricClaimedVerifiedStatus
1LFattNetBadPix(0.01)17.23Unverified
#ModelMetricClaimedVerifiedStatus
1LightDepthNumber of parameters (M)42.6Unverified
#ModelMetricClaimedVerifiedStatus
1UniFuseAbs Rel0.11Unverified
#ModelMetricClaimedVerifiedStatus
1X-TC (Cross-Task Consistency)L1 error1.63Unverified