HMS-Net: Hierarchical Multi-scale Sparsity-invariant Network for Sparse Depth Completion

08/27/2018
by   Zixuan Huang, et al.
4

Dense depth cues are important and have wide applications in various computer vision tasks. In autonomous driving, LIDAR sensors are adopted to acquire depth measurements around the vehicle to perceive the surrounding environments. However, depth maps obtained by LIDAR are generally sparse because of its hardware limitation. The task of depth completion attracts increasing attention, which aims at generating a dense depth map from an input sparse depth map. To effectively utilize multi-scale features, we propose three novel sparsity-invariant operations, based on which, a sparsity-invariant multi-scale encoder-decoder network (HMS-Net) for handling sparse inputs and sparse feature maps is also proposed. Additional RGB features could be incorporated to further improve the depth completion performance. Our extensive experiments and component analysis on two public benchmarks, KITTI depth completion benchmark and NYU-depth-v2 dataset, demonstrate the effectiveness of the proposed approach. As of Aug. 12th, 2018, on KITTI depth completion leaderboard, our proposed model without RGB guidance ranks first among all peer-reviewed methods without using RGB information, and our model with RGB guidance ranks second among all RGB-guided methods.

READ FULL TEXT

page 1

page 2

page 9

page 10

page 11

research
07/14/2021

DVMN: Dense Validity Mask Network for Depth Completion

LiDAR depth maps provide environmental guidance in a variety of applicat...
research
08/30/2022

Spacecraft depth completion based on the gray image and the sparse depth map

Perceiving the three-dimensional (3D) structure of the spacecraft is a p...
research
07/14/2021

PDC: Piecewise Depth Completion utilizing Superpixels

Depth completion from sparse LiDAR and high-resolution RGB data is one o...
research
07/23/2019

Conf-Net: Predicting Depth Completion Error-Map For High-Confidence Dense 3D Point-Cloud

This work proposes a new method for depth completion of sparse LiDAR dat...
research
07/23/2019

Conf-Net: Predicting Depth Completion Error-Map ForHigh-Confidence Dense 3D Point-Cloud

This work proposes a new method for depth completion of sparse LiDAR dat...
research
12/29/2022

PanDepth: Joint Panoptic Segmentation and Depth Completion

Understanding 3D environments semantically is pivotal in autonomous driv...
research
08/03/2020

Project to Adapt: Domain Adaptation for Depth Completion from Noisy and Sparse Sensor Data

Depth completion aims to predict a dense depth map from a sparse depth i...

Please sign up or login with your details

Forgot password? Click here to reset