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 551600 of 2454 papers

TitleStatusHype
FourierNets enable the design of highly non-local optical encoders for computational imagingCode1
Discrete Cosine Transform Network for Guided Depth Map Super-ResolutionCode1
Revisiting Light Field Rendering with Deep Anti-Aliasing Neural NetworkCode1
VR3Dense: Voxel Representation Learning for 3D Object Detection and Monocular Dense Depth ReconstructionCode1
Learning optical flow from still imagesCode1
Self-supervised Learning of Depth Inference for Multi-view StereoCode1
Multi-View Multi-Person 3D Pose Estimation with Plane Sweep StereoCode1
Objects are Different: Flexible Monocular 3D Object DetectionCode1
S2R-DepthNet: Learning a Generalizable Depth-specific Structural RepresentationCode1
Deep Two-View Structure-from-Motion RevisitedCode1
RGB-D Local Implicit Function for Depth Completion of Transparent ObjectsCode1
Unsupervised Learning of Monocular Depth and Ego-Motion Using Multiple MasksCode1
LED2-Net: Monocular 360 Layout Estimation via Differentiable Depth RenderingCode1
Adaptive Surface Normal Constraint for Depth EstimationCode1
Does it work outside this benchmark? Introducing the Rigid Depth Constructor tool, depth validation dataset construction in rigid scenes for the massesCode1
MINE: Towards Continuous Depth MPI with NeRF for Novel View SynthesisCode1
M3DSSD: Monocular 3D Single Stage Object DetectorCode1
Transformer-Based Attention Networks for Continuous Pixel-Wise PredictionCode1
Monocular Depth Estimation through Virtual-world Supervision and Real-world SfM Self-SupervisionCode1
Beyond Image to Depth: Improving Depth Prediction using EchoesCode1
ES-Net: An Efficient Stereo Matching NetworkCode1
Variational Structured Attention Networks for Deep Visual Representation LearningCode1
Implicit Integration of Superpixel Segmentation into Fully Convolutional NetworksCode1
Self-supervised 3D Representation Learning of Dressed Humans from Social Media VideosCode1
Categorical Depth Distribution Network for Monocular 3D Object DetectionCode1
Boundary-induced and scene-aggregated network for monocular depth predictionCode1
Combining Events and Frames using Recurrent Asynchronous Multimodal Networks for Monocular Depth PredictionCode1
UniFuse: Unidirectional Fusion for 360^ Panorama Depth EstimationCode1
Ground-aware Monocular 3D Object Detection for Autonomous DrivingCode1
PLUMENet: Efficient 3D Object Detection from Stereo ImagesCode1
Monocular Depth Estimation Using Laplacian Pyramid-Based Depth ResidualsCode1
Mesh Reconstruction from Aerial Images for Outdoor Terrain Mapping Using Joint 2D-3D LearningCode1
R-MSFM: Recurrent Multi-Scale Feature Modulation for Monocular Depth EstimatingCode1
Three Ways to Improve Semantic Segmentation with Self-Supervised Depth EstimationCode1
Detecting Invisible PeopleCode1
HR-Depth: High Resolution Self-Supervised Monocular Depth EstimationCode1
GeoNet++: Iterative Geometric Neural Network with Edge-Aware Refinement for Joint Depth and Surface Normal EstimationCode1
ViP-DeepLab: Learning Visual Perception with Depth-aware Video Panoptic SegmentationCode1
Depth estimation from 4D light field videosCode1
DeepVideoMVS: Multi-View Stereo on Video with Recurrent Spatio-Temporal FusionCode1
Dual Pixel Exploration: Simultaneous Depth Estimation and Image RestorationCode1
Monocular 3D Object Detection with Sequential Feature Association and Depth Hint AugmentationCode1
AdaBins: Depth Estimation using Adaptive BinsCode1
Multi-view Depth Estimation using Epipolar Spatio-Temporal NetworksCode1
HoHoNet: 360 Indoor Holistic Understanding with Latent Horizontal FeaturesCode1
Deep Multi-view Depth Estimation with Predicted UncertaintyCode1
SeasonDepth: Cross-Season Monocular Depth Prediction Dataset and Benchmark under Multiple EnvironmentsCode1
Learning a Geometric Representation for Data-Efficient Depth Estimation via Gradient Field and Contrastive LossCode1
Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with TransformersCode1
Unsupervised Monocular Depth Learning in Dynamic ScenesCode1
Show:102550
← PrevPage 12 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