SPNet: Structure preserving network for depth completion
Depth completion aims to predict a dense depth map from a sparse one. Benefiting from the powerful ability of convolutional neural networks, recent depth completion methods have achieved remarkable performance. However, it is still a challenging problem to well preserve accurate depth structures, su...
Main Authors: | Tao Li, Songning Luo, Zhiwei Fan, Qunbing Zhou, Ting Hu |
---|---|
Format: | Article |
Language: | English |
Published: |
Public Library of Science (PLoS)
2023-01-01
|
Series: | PLoS ONE |
Online Access: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9873174/?tool=EBI |
Similar Items
-
SPNet: Structure preserving network for depth completion.
by: Tao Li, et al.
Published: (2023-01-01) -
Lightweight Depth Completion Network with Local Similarity-Preserving Knowledge Distillation
by: Yongseop Jeong, et al.
Published: (2022-09-01) -
Compact Depth-Wise Separable Precise Network for Depth Completion
by: Tianqi Wang, et al.
Published: (2023-01-01) -
An Adaptive Fusion Algorithm for Depth Completion
by: Long Chen, et al.
Published: (2022-06-01) -
Precise depth map upsampling and enhancement based on edge‐preserving fusion filters
by: Ting‐An Chang, et al.
Published: (2018-08-01)