Depth Completion

46 papers with code • 7 benchmarks • 9 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

Most implemented papers

Parse Geometry from a Line: Monocular Depth Estimation with Partial Laser Observation

fangchangma/sparse-to-dense.pytorch 17 Oct 2016

Many standard robotic platforms are equipped with at least a fixed 2D laser range finder and a monocular camera.

Noise-Aware Unsupervised Deep Lidar-Stereo Fusion

XuelianCheng/LidarStereoNet CVPR 2019

In this paper, we present LidarStereoNet, the first unsupervised Lidar-stereo fusion network, which can be trained in an end-to-end manner without the need of ground truth depth maps.

In Defense of Classical Image Processing: Fast Depth Completion on the CPU

kujason/ip_basic 31 Jan 2018

With the rise of data driven deep neural networks as a realization of universal function approximators, most research on computer vision problems has moved away from hand crafted classical image processing algorithms.

Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Camera

fangchangma/self-supervised-depth-completion 1 Jul 2018

Depth completion, the technique of estimating a dense depth image from sparse depth measurements, has a variety of applications in robotics and autonomous driving.

Unsupervised Depth Completion from Visual Inertial Odometry

alexklwong/unsupervised-depth-completion-visual-inertial-odometry 15 May 2019

Our method first constructs a piecewise planar scaffolding of the scene, and then uses it to infer dense depth using the image along with the sparse points.

Indoor Depth Completion with Boundary Consistency and Self-Attention

patrickwu2/Depth-Completion 22 Aug 2019

We utilize self-attention mechanism, previously used in image inpainting fields, to extract more useful information in each layer of convolution so that the complete depth map is enhanced.

Aerial Single-View Depth Completion with Image-Guided Uncertainty Estimation

VIS4ROB-lab/aerial-depth-completion 17 Jan 2020

In this paper, we propose a depth completion and uncertainty estimation approach that better handles the challenges of aerial platforms, such as large viewpoint and depth variations, and limited computing resources.

SuperCaustics: Real-time, open-source simulation of transparent objects for deep learning applications

MMehdiMousavi/SuperCaustics 23 Jul 2021

In particular, these synthetic datasets omit features such as refraction, dispersion and caustics due to limitations in the rendering pipeline.

Advancing Self-supervised Monocular Depth Learning with Sparse LiDAR

AutoAILab/FusionDepth 20 Sep 2021

Unlike the existing methods that use sparse LiDAR mainly in a manner of time-consuming iterative post-processing, our model fuses monocular image features and sparse LiDAR features to predict initial depth maps.

Sparsity Invariant CNNs

PeterTor/sparse_convolution 22 Aug 2017

In this paper, we consider convolutional neural networks operating on sparse inputs with an application to depth upsampling from sparse laser scan data.