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 21012150 of 2454 papers

TitleStatusHype
Generating and Exploiting Probabilistic Monocular Depth EstimatesCode0
Unsupervised Monocular Depth and Ego-motion Learning with Structure and Semantics0
TW-SMNet: Deep Multitask Learning of Tele-Wide Stereo Matching0
Deep Robust Single Image Depth Estimation Neural Network Using Scene Understanding0
Multimodal End-to-End Autonomous Driving0
Towards Scene Understanding: Unsupervised Monocular Depth Estimation With Semantic-Aware Representation0
Recurrent Neural Network for (Un-)Supervised Learning of Monocular Video Visual Odometry and Depth0
Monocular Depth Estimation Using Relative Depth Maps0
Soft Labels for Ordinal Regression0
Connecting the Dots: Learning Representations for Active Monocular Depth Estimation0
FSA-Net: Learning Fine-Grained Structure Aggregation for Head Pose Estimation From a Single ImageCode0
UnOS: Unified Unsupervised Optical-Flow and Stereo-Depth Estimation by Watching VideosCode1
Creative Flow+ DatasetCode0
Learning Non-Volumetric Depth Fusion Using Successive ReprojectionsCode0
Veritatem Dies Aperit - Temporally Consistent Depth Prediction Enabled by a Multi-Task Geometric and Semantic Scene Understanding ApproachCode0
Unsupervised Single Image Underwater Depth EstimationCode0
Fully Hyperbolic Convolutional Neural Networks0
Shift R-CNN: Deep Monocular 3D Object Detection with Closed-Form Geometric Constraints0
Depth Estimation on Underwater Omni-directional Images Using a Deep Neural Network0
SharpNet: Fast and Accurate Recovery of Occluding Contours in Monocular Depth EstimationCode0
Semi-Supervised Monocular Depth Estimation with Left-Right Consistency Using Deep Neural NetworkCode0
How do neural networks see depth in single images?0
PhaseCam3D — Learning Phase Masks for Passive Single View Depth EstimationCode0
Lightweight Monocular Depth Estimation Model by Joint End-to-End Filter pruningCode0
Monocular Depth Estimation with Directional Consistency by Deep Networks0
Multi-task human analysis in still images: 2D/3D pose, depth map, and multi-part segmentation0
Learning Unsupervised Multi-View Stereopsis via Robust Photometric ConsistencyCode0
3D Packing for Self-Supervised Monocular Depth EstimationCode1
WoodScape: A multi-task, multi-camera fisheye dataset for autonomous drivingCode0
TriDepth: Triangular Patch-based Deep Depth Prediction0
Learn Stereo, Infer Mono: Siamese Networks for Self-Supervised, Monocular, Depth EstimationCode0
Structured Prediction using cGANs with Fusion Discriminator0
Web Stereo Video Supervision for Depth Prediction from Dynamic Scenes0
Learning the Depths of Moving People by Watching Frozen People0
DeepPerimeter: Indoor Boundary Estimation from Posed Monocular Sequences0
Student Becoming the Master: Knowledge Amalgamation for Joint Scene Parsing, Depth Estimation, and More0
A Large RGB-D Dataset for Semi-supervised Monocular Depth Estimation0
Deep Optics for Monocular Depth Estimation and 3D Object Detection0
Online Adaptation through Meta-Learning for Stereo Depth Estimation0
Multi-Scale Geometric Consistency Guided Multi-View Stereo0
Recurrent Neural Network for (Un-)supervised Learning of Monocular VideoVisual Odometry and DepthCode0
PIV-Based 3D Fluid Flow Reconstruction Using Light Field Camera0
Multi-View Stereo by Temporal Nonparametric FusionCode0
Learning Single Camera Depth Estimation using Dual-PixelsCode0
Absolute Human Pose Estimation with Depth Prediction NetworkCode0
Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown CamerasCode0
Learning Across Tasks and DomainsCode0
Non-Lambertian Surface Shape and Reflectance Reconstruction Using Concentric Multi-Spectral Light Field0
Learning monocular depth estimation infusing traditional stereo knowledgeCode0
Visualization of Convolutional Neural Networks for Monocular Depth EstimationCode0
Show:102550
← PrevPage 43 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