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

Showing 125 of 242 papers

TitleStatusHype
Dynamic Spatial Propagation Network for Depth CompletionCode2
Virtual Sparse Convolution for Multimodal 3D Object DetectionCode2
Bilateral Propagation Network for Depth CompletionCode2
OGNI-DC: Robust Depth Completion with Optimization-Guided Neural IterationsCode2
Sparse Fuse Dense: Towards High Quality 3D Detection with Depth CompletionCode2
CompletionFormer: Depth Completion with Convolutions and Vision TransformersCode2
OMNI-DC: Highly Robust Depth Completion with Multiresolution Depth IntegrationCode2
Depth Completion using Geometry-Aware EmbeddingCode1
Learning an Efficient Multimodal Depth Completion ModelCode1
Learning Topology from Synthetic Data for Unsupervised Depth CompletionCode1
Helvipad: A Real-World Dataset for Omnidirectional Stereo Depth EstimationCode1
Learnable Differencing Center for Nighttime Depth PerceptionCode1
A Concise but High-performing Network for Image Guided Depth Completion in Autonomous DrivingCode1
Dense Depth Priors for Neural Radiance Fields from Sparse Input ViewsCode1
FDCT: Fast Depth Completion for Transparent ObjectsCode1
ClearPose: Large-scale Transparent Object Dataset and BenchmarkCode1
FinnWoodlands DatasetCode1
A Two-Stage Masked Autoencoder Based Network for Indoor Depth CompletionCode1
Advancing Self-supervised Monocular Depth Learning with Sparse LiDARCode1
DEPTHOR: Depth Enhancement from a Practical Light-Weight dToF Sensor and RGB ImageCode1
Aerial Single-View Depth Completion with Image-Guided Uncertainty EstimationCode1
CFPNet: Improving Lightweight ToF Depth Completion via Cross-zone Feature PropagationCode1
Depth Completion with Twin Surface Extrapolation at Occlusion BoundariesCode1
GraphCSPN: Geometry-Aware Depth Completion via Dynamic GCNsCode1
A Surface Geometry Model for LiDAR Depth CompletionCode1
Show:102550
← PrevPage 1 of 10Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SparseConvsRMSE1,601Unverified
2NConv-CNNRMSE1,268Unverified
3VOICEDRMSE1,169.97Unverified
4ScaffNet-FusionNetRMSE1,121.93Unverified
5KBNetRMSE1,069.47Unverified
6Spade-sDRMSE1,035Unverified
7HMS-NetRMSE937Unverified
8Spade-RGBsDRMSE918Unverified
9NConv-CNN-L1RMSE859Unverified
10NConv-CNN-L2RMSE830Unverified
#ModelMetricClaimedVerifiedStatus
1SS-S2DMAE178.85Unverified
2DDPMAE151.86Unverified
3VOICEDMAE85.05Unverified
4ScaffNet-FusionNetMAE59.53Unverified
5KBNetMAE39.8Unverified
6NLSPNMAE26.74Unverified
#ModelMetricClaimedVerifiedStatus
1Struct-MDCRMSE0.14Unverified
2DSNRMSE0.1Unverified
3NLSPNRMSE0.09Unverified
#ModelMetricClaimedVerifiedStatus
1SA+SSIM+BCRMSE1.09Unverified
2DM-LRN-b4RMSE1Unverified
#ModelMetricClaimedVerifiedStatus
1FusionDepthRMSE1,193.92Unverified
#ModelMetricClaimedVerifiedStatus
1CFCNetRMSE 2.96Unverified
#ModelMetricClaimedVerifiedStatus
1DSNREL0.02Unverified
#ModelMetricClaimedVerifiedStatus
1Struct-MDCMAE1,170.3Unverified
#ModelMetricClaimedVerifiedStatus
1Struct-MDCMAE111.33Unverified