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 51–100 of 2454 papers

TitleStatusHype
Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single ImageCode3
GenWarp: Single Image to Novel Views with Semantic-Preserving Generative WarpingCode3
Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous DrivingCode3
DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular VideosCode3
RoadBEV: Road Surface Reconstruction in Bird's Eye ViewCode3
ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth EstimationCode3
What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?Code3
MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View StereoCode3
Denoising Vision TransformersCode3
PatchFusion: An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth EstimationCode3
iDisc: Internal Discretization for Monocular Depth EstimationCode3
VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene CompletionCode3
Unifying Flow, Stereo and Depth EstimationCode3
SimpleRecon: 3D Reconstruction Without 3D ConvolutionsCode3
Towards Accurate Reconstruction of 3D Scene Shape from A Single Monocular ImageCode3
Vision Transformers for Dense PredictionCode3
Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset TransferCode3
Test3R: Learning to Reconstruct 3D at Test TimeCode2
HoloTime: Taming Video Diffusion Models for Panoramic 4D Scene GenerationCode2
Seurat: From Moving Points to DepthCode2
POMATO: Marrying Pointmap Matching with Temporal Motion for Dynamic 3D ReconstructionCode2
A Unified Image-Dense Annotation Generation Model for Underwater ScenesCode2
DepthMaster: Taming Diffusion Models for Monocular Depth EstimationCode2
Driv3R: Learning Dense 4D Reconstruction for Autonomous DrivingCode2
TACO: Learning Multi-modal Action Models with Synthetic Chains-of-Thought-and-ActionCode2
PanoDreamer: Optimization-Based Single Image to 360 3D Scene With DiffusionCode2
Boost 3D Reconstruction using Diffusion-based Monocular Camera CalibrationCode2
SPARS3R: Semantic Prior Alignment and Regularization for Sparse 3D ReconstructionCode2
OSMLoc: Single Image-Based Visual Localization in OpenStreetMap with Fused Geometric and Semantic GuidanceCode2
On Deep Learning for Geometric and Semantic Scene Understanding Using On-Vehicle 3D LiDARCode2
ImOV3D: Learning Open-Vocabulary Point Clouds 3D Object Detection from Only 2D ImagesCode2
MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error PriorsCode2
TIPS: Text-Image Pretraining with Spatial AwarenessCode2
Few-shot Novel View Synthesis using Depth Aware 3D Gaussian SplattingCode2
Refinement of Monocular Depth Maps via Multi-View Differentiable RenderingCode2
Event-based Stereo Depth Estimation: A SurveyCode2
CVT-Occ: Cost Volume Temporal Fusion for 3D Occupancy PredictionCode2
PrimeDepth: Efficient Monocular Depth Estimation with a Stable Diffusion PreimageCode2
Plane2Depth: Hierarchical Adaptive Plane Guidance for Monocular Depth EstimationCode2
HybridDepth: Robust Metric Depth Fusion by Leveraging Depth from Focus and Single-Image PriorsCode2
Diffusion Models for Monocular Depth Estimation: Overcoming Challenging ConditionsCode2
Mono-ViFI: A Unified Learning Framework for Self-supervised Single- and Multi-frame Monocular Depth EstimationCode2
Temporally Consistent Stereo MatchingCode2
IDOL: Unified Dual-Modal Latent Diffusion for Human-Centric Joint Video-Depth GenerationCode2
OPEN: Object-wise Position Embedding for Multi-view 3D Object DetectionCode2
GeoBench: Benchmarking and Analyzing Monocular Geometry Estimation ModelsCode2
DurLAR: A High-fidelity 128-channel LiDAR Dataset with Panoramic Ambient and Reflectivity Imagery for Multi-modal Autonomous Driving ApplicationsCode2
EndoDAC: Efficient Adapting Foundation Model for Self-Supervised Depth Estimation from Any Endoscopic CameraCode2
SPIdepth: Strengthened Pose Information for Self-supervised Monocular Depth EstimationCode2
MonoCD: Monocular 3D Object Detection with Complementary DepthsCode2
Show:102550
← PrevPage 2 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