Depth Completion
77 papers with code • 9 benchmarks • 10 datasets
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
Benchmarks
These leaderboards are used to track progress in Depth Completion
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Datasets
KITTI
NYUv2
Matterport3D
VOID
KITTI-Depth
TransCG
SuperCaustics
BIDCD
PLAD
Latest papers
LiDAR Meta Depth Completion
While using a single model, our method yields significantly better results than a non-adaptive baseline trained on different LiDAR patterns.
FDCT: Fast Depth Completion for Transparent Objects
nonmy/fdct
•
•
To address these challenges, we propose a Fast Depth Completion framework for Transparent objects (FDCT), which also benefits downstream tasks like object pose estimation.
CompletionFormer: Depth Completion with Convolutions and Vision Transformers
youmi-zym/completionformer
•
•
CVPR 2023
This hybrid architecture naturally benefits both the local connectivity of convolutions and the global context of the Transformer in one single model.
Prior based Sampling for Adaptive LiDAR
We propose SampleDepth, a Convolutional Neural Network (CNN), that is suited for an adaptive LiDAR.
FinnWoodlands Dataset
Besides tree trunks, we also annotated "Obstacles" objects as instances as well as the semantic stuff classes "Lake", "Ground", and "Track".
Monocular Visual-Inertial Depth Estimation
isl-org/vi-depth
•
•
We evaluate on the TartanAir and VOID datasets, observing up to 30% reduction in inverse RMSE with dense scale alignment relative to performing just global alignment alone.
Virtual Sparse Convolution for Multimodal 3D Object Detection
hailanyi/virconv
•
•
CVPR 2023
Finally, we develop a semi-supervised pipeline VirConv-S based on a pseudo-label framework.
PanDepth: Joint Panoptic Segmentation and Depth Completion
Understanding 3D environments semantically is pivotal in autonomous driving applications where multiple computer vision tasks are involved.
Sparsity Agnostic Depth Completion
We present a novel depth completion approach agnostic to the sparsity of depth points, that is very likely to vary in many practical applications.
GraphCSPN: Geometry-Aware Depth Completion via Dynamic GCNs
xinliu20/graphcspn_eccv2022
•
•
First, unlike previous methods, we leverage convolution neural networks as well as graph neural networks in a complementary way for geometric representation learning.
