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 12511300 of 2454 papers

TitleStatusHype
Towards Domain-agnostic Depth CompletionCode1
Depth Field Networks for Generalizable Multi-view Scene RepresentationCode2
Monocular 3D Object Detection with Depth from MotionCode2
Seeing Far in the Dark with Patterned FlashCode0
Cost Volume Pyramid Network with Multi-strategies Range Searching for Multi-view StereoCode1
RA-Depth: Resolution Adaptive Self-Supervised Monocular Depth EstimationCode1
Multi-Event-Camera Depth Estimation and Outlier Rejection by Refocused Events FusionCode1
Latent Discriminant deterministic UncertaintyCode1
Learning Depth from Focus in the WildCode1
Densely Constrained Depth Estimator for Monocular 3D Object DetectionCode1
Focal-WNet: An Architecture Unifying Convolution and Attention for Depth EstimationCode0
SelectionConv: Convolutional Neural Networks for Non-rectilinear Image DataCode0
DID-M3D: Decoupling Instance Depth for Monocular 3D Object DetectionCode1
MonoIndoor++:Towards Better Practice of Self-Supervised Monocular Depth Estimation for Indoor Environments0
Mutual Adaptive Reasoning for Monocular 3D Multi-Person Pose Estimation0
DiffuStereo: High Quality Human Reconstruction via Diffusion-based Stereo Using Sparse Cameras0
JPerceiver: Joint Perception Network for Depth, Pose and Layout Estimation in Driving ScenesCode1
BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural NetworksCode1
Adversarial Attacks on Monocular Pose EstimationCode0
Robust and accurate depth estimation by fusing LiDAR and Stereo0
Joint Prediction of Monocular Depth and Structure using Planar and Parallax Geometry0
Towards Scale-Aware, Robust, and Generalizable Unsupervised Monocular Depth Estimation by Integrating IMU Motion DynamicsCode2
Hybrid Skip: A Biologically Inspired Skip Connection for the UNet Architecture0
Physical Attack on Monocular Depth Estimation with Optimal Adversarial PatchesCode1
Depth Perspective-aware Multiple Object Tracking0
Depthformer : Multiscale Vision Transformer For Monocular Depth Estimation With Local Global Information FusionCode1
Direct Handheld Burst Imaging to Simulated Defocus0
BlindSpotNet: Seeing Where We Cannot See0
False Negative Reduction in Semantic Segmentation under Domain Shift using Depth EstimationCode0
DRL-ISP: Multi-Objective Camera ISP with Deep Reinforcement Learning0
Network Binarization via Contrastive LearningCode1
Gaze-Vergence-Controlled See-Through Vision in Augmented Reality0
Multiview Detection with Cardboard Human ModelingCode0
Can Language Understand Depth?Code1
Beyond Visual Field of View: Perceiving 3D Environment with Echoes and Vision0
PS^2F: Polarized Spiral Point Spread Function for Single-Shot 3D Sensing0
Recovering Detail in 3D Shapes Using Disparity Maps0
How Far Can I Go ? : A Self-Supervised Approach for Deterministic Video Depth ForecastingCode0
When the Sun Goes Down: Repairing Photometric Losses for All-Day Depth EstimationCode1
Accurate and Real-time Pseudo Lidar Detection: Is Stereo Neural Network Really Necessary?0
MGNet: Monocular Geometric Scene Understanding for Autonomous DrivingCode1
LaRa: Latents and Rays for Multi-Camera Bird's-Eye-View Semantic SegmentationCode1
Monocular Depth Decomposition of Semi-Transparent Volume RenderingsCode0
Monocular Spherical Depth Estimation with Explicitly Connected Weak Layout Cues0
A High Resolution Multi-exposure Stereoscopic Image & Video Database of Natural Scenes0
BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object DetectionCode2
Semantics-Depth-Symbiosis: Deeply Coupled Semi-Supervised Learning of Semantics and Depth0
MEStereo-Du2CNN: A Novel Dual Channel CNN for Learning Robust Depth Estimates from Multi-exposure Stereo Images for HDR 3D Applications0
0/1 Deep Neural Networks via Block Coordinate Descent0
Analysis & Computational Complexity Reduction of Monocular and Stereo Depth Estimation TechniquesCode0
Show:102550
← PrevPage 26 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