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
VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene CompletionCode3
DROID-Splat: Combining end-to-end SLAM with 3D Gaussian SplattingCode3
Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single VideoCode3
DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular VideosCode3
Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous DrivingCode3
What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?Code3
RoadBEV: Road Surface Reconstruction in Bird's Eye ViewCode3
SimpleRecon: 3D Reconstruction Without 3D ConvolutionsCode3
Relative Pose Estimation through Affine Corrections of Monocular Depth PriorsCode3
Towards Accurate Reconstruction of 3D Scene Shape from A Single Monocular ImageCode3
Depth Any Camera: Zero-Shot Metric Depth Estimation from Any CameraCode3
Denoising Vision TransformersCode3
iDisc: Internal Discretization for Monocular Depth EstimationCode3
PatchFusion: An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth EstimationCode3
DEFOM-Stereo: Depth Foundation Model Based Stereo MatchingCode3
PF3plat: Pose-Free Feed-Forward 3D Gaussian SplattingCode3
Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset TransferCode3
NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object DetectionCode2
Neural Ray Surfaces for Self-Supervised Learning of Depth and Ego-motionCode2
CompletionFormer: Depth Completion with Convolutions and Vision TransformersCode2
MUTR3D: A Multi-camera Tracking Framework via 3D-to-2D QueriesCode2
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth EstimationCode2
Mono-ViFI: A Unified Learning Framework for Self-supervised Single- and Multi-frame Monocular Depth EstimationCode2
MultiMAE: Multi-modal Multi-task Masked AutoencodersCode2
Monocular 3D Object Detection with Depth from MotionCode2
Consistent Video Depth EstimationCode2
MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error PriorsCode2
Multi-Task Learning as Multi-Objective OptimizationCode2
OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free EnvironmentsCode2
Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth EstimationCode2
Map-free Visual Relocalization: Metric Pose Relative to a Single ImageCode2
Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language ReasoningCode2
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
Boost 3D Reconstruction using Diffusion-based Monocular Camera CalibrationCode2
IDOL: Unified Dual-Modal Latent Diffusion for Human-Centric Joint Video-Depth GenerationCode2
Kick Back & Relax++: Scaling Beyond Ground-Truth Depth with SlowTV & CribsTVCode2
MonoCD: Monocular 3D Object Detection with Complementary DepthsCode2
On Deep Learning for Geometric and Semantic Scene Understanding Using On-Vehicle 3D LiDARCode2
GeoBench: Benchmarking and Analyzing Monocular Geometry Estimation ModelsCode2
GeoMVSNet: Learning Multi-View Stereo With Geometry PerceptionCode2
BEVStereo: Enhancing Depth Estimation in Multi-view 3D Object Detection with Dynamic Temporal StereoCode2
GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View SynthesisCode2
BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object DetectionCode2
Few-shot Novel View Synthesis using Depth Aware 3D Gaussian SplattingCode2
HoloTime: Taming Video Diffusion Models for Panoramic 4D Scene GenerationCode2
ImOV3D: Learning Open-Vocabulary Point Clouds 3D Object Detection from Only 2D ImagesCode2
InstructCV: Instruction-Tuned Text-to-Image Diffusion Models as Vision GeneralistsCode2
Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution MergingCode2
EndoDAC: Efficient Adapting Foundation Model for Self-Supervised Depth Estimation from Any Endoscopic CameraCode2
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