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 101–150 of 2454 papers

TitleStatusHype
CVT-Occ: Cost Volume Temporal Fusion for 3D Occupancy PredictionCode2
Physical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous DrivingCode2
MonoCD: Monocular 3D Object Detection with Complementary DepthsCode2
CompletionFormer: Depth Completion with Convolutions and Vision TransformersCode2
Monocular 3D Object Detection with Depth from MotionCode2
Refinement of Monocular Depth Maps via Multi-View Differentiable RenderingCode2
MultiMAE: Multi-modal Multi-task Masked AutoencodersCode2
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth EstimationCode2
Deep3D: Fully Automatic 2D-to-3D Video Conversion with Deep Convolutional Neural NetworksCode2
RoboDepth: Robust Out-of-Distribution Depth Estimation under CorruptionsCode2
Map-free Visual Relocalization: Metric Pose Relative to a Single ImageCode2
360MonoDepth: High-Resolution 360deg Monocular Depth EstimationCode2
Self-Supervised Learning from Images with a Joint-Embedding Predictive ArchitectureCode2
Semantically-Guided Representation Learning for Self-Supervised Monocular DepthCode2
Single-View View Synthesis in the Wild with Learned Adaptive Multiplane ImagesCode2
SPARS3R: Semantic Prior Alignment and Regularization for Sparse 3D ReconstructionCode2
SPIdepth: Strengthened Pose Information for Self-supervised Monocular Depth EstimationCode2
SuperFusion: Multilevel LiDAR-Camera Fusion for Long-Range HD Map GenerationCode2
Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth EstimationCode2
Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language ReasoningCode2
The RoboDepth Challenge: Methods and Advancements Towards Robust Depth EstimationCode2
Learning to Recover 3D Scene Shape from a Single ImageCode2
Joint 2D-3D Multi-Task Learning on Cityscapes-3D: 3D Detection, Segmentation, and Depth EstimationCode2
A Simple Framework for 3D Occupancy Estimation in Autonomous DrivingCode2
Kick Back & Relax++: Scaling Beyond Ground-Truth Depth with SlowTV & CribsTVCode2
OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free EnvironmentsCode2
HybridDepth: Robust Metric Depth Fusion by Leveraging Depth from Focus and Single-Image PriorsCode2
HoloTime: Taming Video Diffusion Models for Panoramic 4D Scene GenerationCode2
GeoMVSNet: Learning Multi-View Stereo With Geometry PerceptionCode2
GeoBench: Benchmarking and Analyzing Monocular Geometry Estimation ModelsCode2
GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View SynthesisCode2
IDOL: Unified Dual-Modal Latent Diffusion for Human-Centric Joint Video-Depth GenerationCode2
Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution MergingCode2
Boost 3D Reconstruction using Diffusion-based Monocular Camera CalibrationCode2
Adaptive Fusion of Single-View and Multi-View Depth for Autonomous DrivingCode2
Few-shot Novel View Synthesis using Depth Aware 3D Gaussian SplattingCode2
BinsFormer: Revisiting Adaptive Bins for Monocular Depth EstimationCode2
ImOV3D: Learning Open-Vocabulary Point Clouds 3D Object Detection from Only 2D ImagesCode2
BEVStereo: Enhancing Depth Estimation in Multi-view 3D Object Detection with Dynamic Temporal StereoCode2
DurLAR: A High-fidelity 128-channel LiDAR Dataset with Panoramic Ambient and Reflectivity Imagery for Multi-modal Autonomous Driving ApplicationsCode2
EA-LSS: Edge-aware Lift-splat-shot Framework for 3D BEV Object DetectionCode2
EndoDAC: Efficient Adapting Foundation Model for Self-Supervised Depth Estimation from Any Endoscopic CameraCode2
BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object DetectionCode2
Driv3R: Learning Dense 4D Reconstruction for Autonomous DrivingCode2
Behind the Scenes: Density Fields for Single View ReconstructionCode2
Enforcing geometric constraints of virtual normal for depth predictionCode2
Diffusion Models for Monocular Depth Estimation: Overcoming Challenging ConditionsCode2
A Unified Image-Dense Annotation Generation Model for Underwater ScenesCode2
Depth-Regularized Optimization for 3D Gaussian Splatting in Few-Shot ImagesCode2
DiffusionDepth: Diffusion Denoising Approach for Monocular Depth EstimationCode2
Show:102550
← PrevPage 3 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