Noise-Aware Unsupervised Deep Lidar-Stereo Fusion (2019-04-08T00:00:00.000000Z)

TL;DR

LidarStereoNet is presented, 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, and is proposed to incorporate the piecewise planar model into the network learning to further constrain depths to conform to the underlying 3D geometry.

Abstract

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. By introducing a novel ``Feedback Loop'' to connect the network input with output, LidarStereoNet could tackle both noisy Lidar points and misalignment between sensors that have been ignored in existing Lidar-stereo fusion work. Besides, we propose to incorporate the piecewise planar model into the network learning to further constrain depths to conform to the underlying 3D geometry. Extensive quantitative and qualitative evaluations on both real and synthetic datasets demonstrate the superiority of our method, which outperforms state-of-the-art stereo matching, depth completion and Lidar-Stereo fusion approaches significantly.

Authors

Yuchao Dai

10 papers

Hongdong Li

11 papers

Yiran Zhong

6 papers

TL;DR

Abstract

Authors

References36 items

Open-World Stereo Video Matching with Deep RNN

Sparse and Dense Data with CNNs: Depth Completion and Semantic Segmentation

ActiveStereoNet: End-to-End Self-Supervised Learning for Active Stereo Systems

High-Precision Depth Estimation with the 3D LiDAR and Stereo Fusion

Pyramid Stereo Matching Network

Deep Convolutional Compressed Sensing for LiDAR Depth Completion

Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Image

Self-Supervised Learning for Stereo Matching with Self-Improving Ability

Sparsity Invariant CNNs

End-to-End Learning of Geometry and Context for Deep Stereo Regression

Real-time probabilistic fusion of sparse 3D LIDAR and dense stereo

Unsupervised Monocular Depth Estimation with Left-Right Consistency

Semantically Guided Depth Upsampling

The SYNTHIA Dataset: A Large Collection of Synthetic Images for Semantic Segmentation of Urban Scenes

Deeper Depth Prediction with Fully Convolutional Residual Networks

A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation

MeshStereo: A Global Stereo Model with Mesh Alignment Regularization for View Interpolation

Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches

Joint 3d Estimation of Vehicles and Scene Flow

Efficient Joint Segmentation, Occlusion Labeling, Stereo and Flow Estimation

Depth Map Prediction from a Single Image using a Multi-Scale Deep Network

SLIC Superpixels Compared to State-of-the-Art Superpixel Methods

Are we ready for autonomous driving? The KITTI vision benchmark suite

High-resolution depth maps based on TOF-stereo fusion

StereoScan: Dense 3d reconstruction in real-time

Towards fully autonomous driving: Systems and algorithms

Integrating LIDAR into Stereo for Fast and Improved Disparity Computation

Visual-Inertial Sensor Fusion: Localization, Mapping and Sensor-to-Sensor Self-calibration

Processing Dense Stereo Data Using Elevation Maps: Road Surface, Traffic Isle, and Obstacle Detection

Integrating 3D laser scanning and photogrammetry for progress measurement of construction work

A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms

Lidar measurement of snow depth: a review

Image and Sparse Laser Fusion for Dense Scene Reconstruction

Improving path planning and mapping based on stereo vision and lidar

Fusion of Lidar and Stereo Range for Mobile Robots

Ieee Transactions on Pattern Analysis and Machine Intelligence 1 Stereo Processing by Semi-global Matching and Mutual Information

Field of Study

Journal Information

Name

Page

Venue Information

Name

Type

URL

Alternate Names