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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 76–100 of 242 papers

Title	Date	Tasks	Status	Score
Propagating Confidences through CNNs for Sparse Data Regression	May 30, 2018	Autonomous DrivingDepth Completion	CodeCode Available	5
Radar-Camera Pixel Depth Association for Depth Completion	Jun 5, 2021	Depth Completion	CodeCode Available	5
Sparse and noisy LiDAR completion with RGB guidance and uncertainty	Feb 14, 2019	Autonomous VehiclesDepth Completion	CodeCode Available	5
Multi-Modal Masked Pre-Training for Monocular Panoramic Depth Completion	Mar 18, 2022	Depth CompletionTransfer Learning	CodeCode Available	5
AugUndo: Scaling Up Augmentations for Monocular Depth Completion and Estimation	Oct 15, 2023	Data AugmentationDepth Completion	CodeCode Available	5
DFuseNet: Deep Fusion of RGB and Sparse Depth Information for Image Guided Dense Depth Completion	Feb 2, 2019	Depth CompletionSuper-Resolution	CodeCode Available	5
MIPI 2022 Challenge on RGB+ToF Depth Completion: Dataset and Report	Sep 15, 2022	Depth Completion	CodeCode Available	5
Evaluating Scalable Bayesian Deep Learning Methods for Robust Computer Vision	Jun 4, 2019	Deep LearningDepth Completion	CodeCode Available	5
3D LiDAR and Stereo Fusion using Stereo Matching Network with Conditional Cost Volume Normalization	Apr 5, 2019	Depth CompletionStereo-LiDAR Fusion	CodeCode Available	5
FCDSN-DC: An Accurate and Lightweight Convolutional Neural Network for Stereo Estimation with Depth Completion	Sep 14, 2022	Depth CompletionMissing Values	CodeCode Available	5
Prior based Sampling for Adaptive LiDAR	Apr 14, 2023	Depth Completion	CodeCode Available	5
NeSLAM: Neural Implicit Mapping and Self-Supervised Feature Tracking With Depth Completion and Denoising	Mar 29, 2024	3D ReconstructionDenoising	CodeCode Available	5
Conf-Net: Toward High-Confidence Dense 3D Point-Cloud with Error-Map Prediction	Jul 23, 2019	Autonomous DrivingDepth Completion	CodeCode Available	5
Adaptive LiDAR Sampling and Depth Completion using Ensemble Variance	Jul 27, 2020	Autonomous VehiclesDepth Completion	CodeCode Available	5
Masked Spatial Propagation Network for Sparsity-Adaptive Depth Refinement	Apr 30, 2024	Depth Completion	CodeCode Available	5
Confidence Propagation through CNNs for Guided Sparse Depth Regression	Nov 5, 2018	Autonomous DrivingDepth Completion	CodeCode Available	5
DepthNet: Real-Time LiDAR Point Cloud Depth Completion for Autonomous Vehicles	Jul 5, 2020	Autonomous DrivingAutonomous Vehicles	CodeCode Available	5
Unsupervised Depth Completion from Visual Inertial Odometry	May 15, 2019	Depth Completion	CodeCode Available	5
Learning Depth with Convolutional Spatial Propagation Network	Oct 4, 2018	Depth CompletionDepth Estimation	CodeCode Available	5
Indoor Depth Completion with Boundary Consistency and Self-Attention	Aug 22, 2019	Depth CompletionDepth Estimation	CodeCode Available	5
In Defense of Classical Image Processing: Fast Depth Completion on the CPU	Jan 31, 2018	CPUDepth Completion	CodeCode Available	5
Learning Guided Convolutional Network for Depth Completion	Aug 3, 2019	Autonomous DrivingDepth Completion	CodeCode Available	5
Noise-Aware Unsupervised Deep Lidar-Stereo Fusion	Apr 8, 2019	3D geometryDepth Completion	CodeCode Available	5
Sparse and noisy LiDAR completion with RGB guidance anduncertainty	Feb 14, 2019	Autonomous VehiclesDepth Completion	CodeCode Available	5
Depth Completion via Deep Basis Fitting	Dec 21, 2019	Depth Completion	—Unverified	0

Show:10 25 50

← PrevPage 4 of 10Next →

All datasets KITTI Depth Completion VOID NYU-Depth V2 Matterport3D KITTI KITTI Depth Completion 500 points KITTI Depth Completion Eigen Split PLAD VOID-150

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	SparseConvs	RMSE	1,601	—	Unverified
2	NConv-CNN	RMSE	1,268	—	Unverified
3	VOICED	RMSE	1,169.97	—	Unverified
4	ScaffNet-FusionNet	RMSE	1,121.93	—	Unverified
5	KBNet	RMSE	1,069.47	—	Unverified
6	Spade-sD	RMSE	1,035	—	Unverified
7	HMS-Net	RMSE	937	—	Unverified
8	Spade-RGBsD	RMSE	918	—	Unverified
9	NConv-CNN-L1	RMSE	859	—	Unverified
10	NConv-CNN-L2	RMSE	830	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SS-S2D	MAE	178.85	—	Unverified
2	DDP	MAE	151.86	—	Unverified
3	VOICED	MAE	85.05	—	Unverified
4	ScaffNet-FusionNet	MAE	59.53	—	Unverified
5	KBNet	MAE	39.8	—	Unverified
6	NLSPN	MAE	26.74	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Struct-MDC	RMSE	0.14	—	Unverified
2	DSN	RMSE	0.1	—	Unverified
3	NLSPN	RMSE	0.09	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SA+SSIM+BC	RMSE	1.09	—	Unverified
2	DM-LRN-b4	RMSE	1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	FusionDepth	RMSE	1,193.92	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CFCNet	RMSE	2.96	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	DSN	REL	0.02	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Struct-MDC	MAE	1,170.3	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Struct-MDC	MAE	111.33	—	Unverified