SOTAVerified

Depth Completion

The Depth Completion task is a sub-problem of depth estimation. In the sparse-to-dense depth completion problem, one wants to infer the dense depth map of a 3-D scene given an RGB image and its corresponding sparse reconstruction in the form of a sparse depth map obtained either from computational methods such as SfM (Strcuture-from-Motion) or active sensors such as lidar or structured light sensors.

Source: LiStereo: Generate Dense Depth Maps from LIDAR and Stereo Imagery , Unsupervised Depth Completion from Visual Inertial Odometry

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 201–242 of 242 papers

TitleStatusHype
Depth Completion Using a View-constrained Deep Prior—0
FIS-Nets: Full-image Supervised Networks for Monocular Depth Estimation—0
Aerial Single-View Depth Completion with Image-Guided Uncertainty EstimationCode1
Don't Forget The Past: Recurrent Depth Estimation from Monocular Video—0
Depth Completion via Deep Basis Fitting—0
CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completion—0
Depth Completion from Sparse LiDAR Data with Depth-Normal Constraints—0
ClearGrasp: 3D Shape Estimation of Transparent Objects for ManipulationCode0
Indoor Depth Completion with Boundary Consistency and Self-AttentionCode0
To complete or to estimate, that is the question: A Multi-Task Approach to Depth Completion and Monocular Depth Estimation—0
Image-Guided Depth Sampling and Reconstruction—0
Learning Guided Convolutional Network for Depth CompletionCode0
Conf-Net: Toward High-Confidence Dense 3D Point-Cloud with Error-Map PredictionCode0
Improving 3D Object Detection for Pedestrians with Virtual Multi-View Synthesis Orientation Estimation—0
S&CNet: Monocular Depth Completion for Autonomous Systems and 3D Reconstruction—0
Deep RGB-D Canonical Correlation Analysis For Sparse Depth CompletionCode0
Generating and Exploiting Probabilistic Monocular Depth EstimatesCode0
Evaluating Scalable Bayesian Deep Learning Methods for Robust Computer VisionCode0
Veritatem Dies Aperit - Temporally Consistent Depth Prediction Enabled by a Multi-Task Geometric and Semantic Scene Understanding ApproachCode0
Unsupervised Depth Completion from Visual Inertial OdometryCode0
Noise-Aware Unsupervised Deep Lidar-Stereo FusionCode0
3D LiDAR and Stereo Fusion using Stereo Matching Network with Conditional Cost Volume NormalizationCode0
Veritatem Dies Aperit- Temporally Consistent Depth Prediction Enabled by a Multi-Task Geometric and Semantic Scene Understanding ApproachCode0
DFineNet: Ego-Motion Estimation and Depth Refinement from Sparse, Noisy Depth Input with RGB Guidance—0
Depth Coefficients for Depth Completion—0
Sparse and noisy LiDAR completion with RGB guidance and uncertaintyCode0
Sparse and noisy LiDAR completion with RGB guidance anduncertaintyCode0
DFuseNet: Deep Fusion of RGB and Sparse Depth Information for Image Guided Dense Depth CompletionCode0
Dense Depth Posterior (DDP) from Single Image and Sparse Range—0
DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color ImageCode0
Confidence Propagation through CNNs for Guided Sparse Depth RegressionCode0
Learning Depth with Convolutional Spatial Propagation NetworkCode0
HMS-Net: Hierarchical Multi-scale Sparsity-invariant Network for Sparse Depth Completion—0
Sparse and Dense Data with CNNs: Depth Completion and Semantic Segmentation—0
Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular CameraCode0
Propagating Confidences through CNNs for Sparse Data RegressionCode0
Deep Depth Completion of a Single RGB-D ImageCode0
Deep Convolutional Compressed Sensing for LiDAR Depth Completion—0
In Defense of Classical Image Processing: Fast Depth Completion on the CPUCode0
Sparsity Invariant CNNsCode0
Parse Geometry from a Line: Monocular Depth Estimation with Partial Laser ObservationCode0
Mutual-Structure for Joint Filtering—0
Show:102550
← PrevPage 5 of 5Next →
All datasetsKITTI Depth CompletionVOIDNYU-Depth V2Matterport3DKITTIKITTI Depth Completion 500 pointsKITTI Depth Completion Eigen SplitPLADVOID-150

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SparseConvsRMSE1,601—Unverified
2NConv-CNNRMSE1,268—Unverified
3VOICEDRMSE1,169.97—Unverified
4ScaffNet-FusionNetRMSE1,121.93—Unverified
5KBNetRMSE1,069.47—Unverified
6Spade-sDRMSE1,035—Unverified
7HMS-NetRMSE937—Unverified
8Spade-RGBsDRMSE918—Unverified
9NConv-CNN-L1RMSE859—Unverified
10NConv-CNN-L2RMSE830—Unverified
#ModelMetricClaimedVerifiedStatus
1SS-S2DMAE178.85—Unverified
2DDPMAE151.86—Unverified
3VOICEDMAE85.05—Unverified
4ScaffNet-FusionNetMAE59.53—Unverified
5KBNetMAE39.8—Unverified
6NLSPNMAE26.74—Unverified
#ModelMetricClaimedVerifiedStatus
1Struct-MDCRMSE0.14—Unverified
2DSNRMSE0.1—Unverified
3NLSPNRMSE0.09—Unverified
#ModelMetricClaimedVerifiedStatus
1SA+SSIM+BCRMSE1.09—Unverified
2DM-LRN-b4RMSE1—Unverified
#ModelMetricClaimedVerifiedStatus
1FusionDepthRMSE1,193.92—Unverified
#ModelMetricClaimedVerifiedStatus
1CFCNetRMSE 2.96—Unverified
#ModelMetricClaimedVerifiedStatus
1DSNREL0.02—Unverified
#ModelMetricClaimedVerifiedStatus
1Struct-MDCMAE1,170.3—Unverified
#ModelMetricClaimedVerifiedStatus
1Struct-MDCMAE111.33—Unverified