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 22012250 of 2454 papers

TitleStatusHype
Fast and Efficient Lenslet Image Compression0
Monocular Depth Estimation: A Survey0
Unsupervised Learning-based Depth Estimation aided Visual SLAM Approach0
Monocular Outdoor Semantic Mapping with a Multi-task Network0
AuxNet: Auxiliary tasks enhanced Semantic Segmentation for Automated Driving0
Real-time Joint Object Detection and Semantic Segmentation Network for Automated Driving0
NRMVS: Non-Rigid Multi-View Stereo0
Exploring Deep Spiking Neural Networks for Automated Driving Applications0
Unsupervised monocular stereo matching0
Wireless Software Synchronization of Multiple Distributed Cameras0
Plug-and-Play: Improve Depth Estimation via Sparse Data PropagationCode0
Learning Common Representation from RGB and Depth Images0
Fast and Accurate Depth Estimation from Sparse Light Fields0
SIGNet: Semantic Instance Aided Unsupervised 3D Geometry PerceptionCode0
Learning Semantic Segmentation from Synthetic Data: A Geometrically Guided Input-Output Adaptation Approach0
DeepV2D: Video to Depth with Differentiable Structure from MotionCode0
Unsupervised Learning of Monocular Depth Estimation with Bundle Adjustment, Super-Resolution and Clip Loss0
Learning to Infer the Depth Map of a Hand from its Color Image0
Inferring Point Clouds from Single Monocular Images by Depth Intermediation0
DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color ImageCode0
Revisiting Multi-Task Learning with ROCK: a Deep Residual Auxiliary Block for Visual DetectionCode0
Event-Based Structured Light for Depth Reconstruction using Frequency Tagged Light Patterns0
UnDEMoN 2.0: Improved Depth and Ego Motion Estimation through Deep Image Sampling0
MonoGRNet: A Geometric Reasoning Network for Monocular 3D Object LocalizationCode0
Double Refinement Network for Efficient Indoor Monocular Depth Estimation0
DSCnet: Replicating Lidar Point Clouds with Deep Sensor Cloning0
Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular VideosCode0
Self-Supervised Learning of Depth and Camera Motion from 360° Videos0
Bi-Real Net: Binarizing Deep Network Towards Real-Network PerformanceCode0
R^3SGM: Real-time Raster-Respecting Semi-Global Matching for Power-Constrained Systems0
Anytime Stereo Image Depth Estimation on Mobile DevicesCode0
DeepLens: Shallow Depth Of Field From A Single Image0
UnrealROX: An eXtremely Photorealistic Virtual Reality Environment for Robotics Simulations and Synthetic Data GenerationCode0
Playing for Depth0
Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic UnderstandingCode0
Geometry meets semantics for semi-supervised monocular depth estimationCode0
Learning Depth with Convolutional Spatial Propagation NetworkCode0
SuperDepth: Self-Supervised, Super-Resolved Monocular Depth Estimation0
CNN-SVO: Improving the Mapping in Semi-Direct Visual Odometry Using Single-Image Depth PredictionCode0
DisNet: A novel method for distance estimation from monocular camera0
Boundary-guided Feature Aggregation Network for Salient Object Detection0
Real-time Dynamic Object Detection for Autonomous Driving using Prior 3D-Maps0
MERCI: A NEW METRIC TO EVALUATE THE CORRELATION BETWEEN PREDICTIVE UNCERTAINTY AND TRUE ERROR0
Sparse-to-Continuous: Enhancing Monocular Depth Estimation using Occupancy MapsCode0
Real Time Dense Depth Estimation by Fusing Stereo with Sparse Depth MeasurementsCode0
GANVO: Unsupervised Deep Monocular Visual Odometry and Depth Estimation with Generative Adversarial Networks0
Style Augmentation: Data Augmentation via Style RandomizationCode0
Real-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric AnnotationsCode0
End-to-end depth from motion with stabilized monocular videos0
Learning structure-from-motion from motion0
Show:102550
← PrevPage 45 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